INDEX

Explanations

references to the September 11 (9/11) attacks

oai_token-act-pair · gpt-3.5-turbo

references to the 9/11 attacks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Tile

-0.70

laus

-0.66

hunt

-0.65

VO

-0.63

arov

-0.63

Kis

-0.63

eva

-0.62

secut

-0.62

 Aberdeen

-0.61

 unman

-0.59

POSITIVE LOGITS

 Syndrome

0.93

 anniversary

0.90

 Truth

0.85

 Anniversary

0.75

abad

0.74

truth

0.74

 mastermind

0.73

âĢ²

0.72

iverse

0.71

 Authorization

0.70

Activations Density 0.021%

references to the September 11 (9/11) attacks

references to the 9/11 attacks

No Comments

No Known Activations