INDEX

Explanations

phrases related to the word "Apple"

oai_token-act-pair · gpt-3.5-turbo

words related to applications and their functionality

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

ï¸ı

-0.78

peed

-0.66

 thirds

-0.66

 knot

-0.66

warts

-0.66

 unanswered

-0.64

ÄŁ

-0.61

 knots

-0.58

SourceFile

-0.56

 Swedish

-0.56

POSITIVE LOGITS

urai

0.86

hof

0.85

olitics

0.82

illin

0.81

ause

0.80

isode

0.78

ertain

0.76

arently

0.72

atre

0.71

ciating

0.70

Activations Density 0.187%

phrases related to the word "Apple"

words related to applications and their functionality

No Comments

No Known Activations