INDEX

Explanations

words related to powerful actions or events

oai_token-act-pair · gpt-3.5-turbo

references to explosions or loud impacts

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

phis

-0.70

 compr

-0.69

guyen

-0.69

ccording

-0.68

Madison

-0.68

tymology

-0.66

Adapt

-0.65

Govern

-0.65

laus

-0.64

prison

-0.64

POSITIVE LOGITS

 furnace

1.00

 blast

0.93

blast

0.90

ographed

0.89

ocy

0.88

asted

0.85

anche

0.84

asts

0.83

 furn

0.82

asting

0.81

Activations Density 0.015%

words related to powerful actions or events

references to explosions or loud impacts

No Comments

No Known Activations