INDEX

Explanations

contractions of words followed by the word "not"

oai_token-act-pair · gpt-3.5-turbo

contractions of the verb "to be" (isn't, aren't, wasn't)

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

PU

-0.77

 Mechdragon

-0.72

 Species

-0.66

 compliment

-0.65

 crotch

-0.65

 Cellular

-0.65

 Draw

-0.65

 deposit

-0.63

 mark

-0.62

 face

-0.61

POSITIVE LOGITS

't

1.49

ÃŃ

0.99

iting

0.98

nas

0.92

ited

0.88

ned

0.86

tyard

0.85

etsk

0.84

ajor

0.84

its

0.83

Activations Density 0.082%

contractions of words followed by the word "not"

contractions of the verb "to be" (isn't, aren't, wasn't)

No Comments

No Known Activations