INDEX

Explanations

direct responses of negation or refusal

oai_token-act-pair · gpt-3.5-turbo

negative responses or denials

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

ortment

-0.72

 reverted

-0.65

kefeller

-0.63

drawn

-0.60

rored

-0.60

sing

-0.58

pez

-0.58

ylan

-0.57

riers

-0.57

abal

-0.57

POSITIVE LOGITS

sir

0.96

 Nope

0.91

terday

0.89

0.88

!,

0.83

!.

0.83

 Absolutely

0.79

 worries

0.78

!!!!

0.77

Activations Density 0.072%

direct responses of negation or refusal

negative responses or denials

No Comments

No Known Activations