INDEX

Explanations

references to proposed legislative actions

oai_token-act-pair · gpt-3.5-turbo

the word "would" indicating future actions or proposals in legislative 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

Ti

-0.72

Tuc

-0.72

 Chal

-0.72

 Velocity

-0.65

 Nile

-0.64

Statistics

-0.64

 Corpus

-0.63

usage

-0.62

values

-0.62

Pie

-0.62

POSITIVE LOGITS

be

1.03

 doubtless

0.97

 introduce

0.96

 likely

0.93

 undoubtedly

0.92

 allow

0.90

 probably

0.88

 eventually

0.87

 surely

0.86

 imply

0.85

Activations Density 0.139%

references to proposed legislative actions

the word "would" indicating future actions or proposals in legislative contexts

No Comments

No Known Activations