INDEX

Explanations

contractions with negations

oai_token-act-pair · gpt-3.5-turbo

phrases expressing uncertainty or lack of knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 misdem

-0.66

 Agency

-0.66

 afore

-0.64

)=(

-0.64

 Passage

-0.63

 awaited

-0.63

ANG

-0.61

 elimination

-0.60

 Passing

-0.60

upp

-0.58

POSITIVE LOGITS

't

1.49

ned

1.05

ates

0.88

essee

0.86

uts

0.85

ÃŃ

0.84

nas

0.82

etsk

0.80

nis

0.79

lv

0.77

Activations Density 0.087%

contractions with negations

phrases expressing uncertainty or lack of knowledge

No Comments

No Known Activations