INDEX

Explanations

words related to significant or important events, especially with a sense of historical importance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "historic" and related references to significant events or contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Downloadha

-0.98

nery

-0.91

cham

-0.82

xia

-0.79

Kids

-0.77

gans

-0.76

atu

-0.76

ullah

-0.76

agher

-0.74

vern

-0.74

POSITIVE LOGITS

 preservation

1.07

 significance

1.00

 landmark

0.99

orically

0.93

 lows

0.89

istically

0.85

orical

0.82

 landmarks

0.81

 Preservation

0.79

 Revival

0.79

Activations Density 0.013%

words related to significant or important events, especially with a sense of historical importance

instances of the word "historic" and related references to significant events or contexts

No Comments

No Known Activations