INDEX

Explanations

word forms related to amputations

oai_token-act-pair · gpt-3.5-turbo

variations of the word "mute."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kell

-0.78

 challeng

-0.71

awaru

-0.70

luster

-0.68

abeth

-0.68

etheless

-0.66

omnia

-0.65

 sidel

-0.64

mith

-0.64

 thirsty

-0.63

POSITIVE LOGITS

culosis

0.93

anamo

0.89

anu

0.85

vich

0.80

lled

0.78

ted

0.77

ople

0.75

xt

0.74

ously

0.73

urs

0.73

Activations Density 0.034%

word forms related to amputations

variations of the word "mute."

No Comments

No Known Activations