INDEX

Explanations

contractions of "would not" or "could not" in text

oai_token-act-pair · gpt-3.5-turbo

expressions of negation or refusal

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

 Cosponsors

-0.64

«ĺ

-0.64

ishing

-0.62

ÃŁ

-0.62

è¦ļéĨĴ

-0.60

\<

-0.59

active

-0.58

Bench

-0.57

xxxx

-0.57

Fil

-0.56

POSITIVE LOGITS

ĸļ

0.80

 tumble

0.70

 offend

0.69

 dearly

0.64

«

0.64

oola

0.63

 fitting

0.62

 unthinkable

0.62

itate

0.61

schild

0.61

Activations Density 0.219%

contractions of "would not" or "could not" in text

expressions of negation or refusal

No Comments

No Known Activations