INDEX

Explanations

references to political positions or ideologies

oai_token-act-pair · gpt-3.5-turbo

references to political extremes or factions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Picks

-0.77

 Peel

-0.71

urated

-0.61

 Bean

-0.60

 Rankings

-0.60

ifully

-0.60

 Ortiz

-0.59

 PROGRAM

-0.58

 Mechanics

-0.58

 Puzzles

-0.58

POSITIVE LOGITS

thing

1.02

 flung

0.98

med

0.97

aday

0.97

fetched

0.96

away

0.92

riers

0.92

rowing

0.90

rier

0.85

seeing

0.78

Activations Density 0.025%

references to political positions or ideologies

references to political extremes or factions

No Comments

No Known Activations