INDEX

Explanations

words related to cooking or food preparation, particularly those related to stewing

oai_token-act-pair · gpt-3.5-turbo

variations of the word "stew" in different forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Fasc

-0.76

Downloadha

-0.73

NetMessage

-0.72

thodox

-0.71

prus

-0.69

opathic

-0.63

ctica

-0.62

anguage

-0.62

itten

-0.62

CPC

-0.61

POSITIVE LOGITS

ards

1.31

 stew

1.17

ard

1.16

arding

1.05

arded

1.05

ARDS

0.95

itect

0.90

 Stew

0.87

ARD

0.87

loads

0.85

Activations Density 0.016%

words related to cooking or food preparation, particularly those related to stewing

variations of the word "stew" in different forms

No Comments

No Known Activations