INDEX

Explanations

words related to formal or regulatory contexts

oai_token-act-pair · gpt-3.5-turbo

lexical items related to formal or academic 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

FFER

-0.75

olicy

-0.74

yi

-0.73

ortium

-0.73

hov

-0.72

lio

-0.72

 tremend

-0.71

ession

-0.70

 Chaser

-0.68

mble

-0.67

POSITIVE LOGITS

ization

1.03

ibur

1.02

axy

0.99

ized

0.99

izing

0.98

istic

0.93

gebra

0.91

pha

0.89

gorith

0.88

uminum

0.88

Activations Density 0.028%

words related to formal or regulatory contexts

lexical items related to formal or academic contexts

No Comments

No Known Activations