INDEX

Explanations

words related to governing and rules

oai_token-act-pair · gpt-3.5-turbo

terms related to governance and authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

uni

-0.68

Veter

-0.65

 Colt

-0.62

 Brist

-0.61

uder

-0.61

Strike

-0.60

Na

-0.59

dain

-0.59

Bron

-0.59

 Strike

-0.58

POSITIVE LOGITS

 govern

1.00

 governing

0.91

orship

0.91

manship

0.87

 governed

0.86

 governs

0.86

govern

0.84

orial

0.83

esses

0.81

iments

0.75

Activations Density 0.010%

words related to governing and rules

terms related to governance and authority

No Comments

No Known Activations