INDEX

Explanations

phrases or words related to symbolizing or exemplifying something

oai_token-act-pair · gpt-3.5-turbo

terms related to representation and symbolism

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

ahs

-0.66

ergic

-0.65

hatt

-0.63

kers

-0.62

secut

-0.61

ithing

-0.60

ahn

-0.59

asive

-0.59

oy

-0.58

 hired

-0.58

POSITIVE LOGITS

uate

0.76

ĸļ

0.76

ĺħ

0.75

enance

0.70

DonaldTrump

0.66

ROR

0.66

Flag

0.66

 Friendship

0.65

 Mata

0.65

lihood

0.65

Activations Density 0.125%

phrases or words related to symbolizing or exemplifying something

terms related to representation and symbolism

No Comments

No Known Activations