INDEX

Explanations

descriptions or reviews of various activities or items

oai_token-act-pair · gpt-3.5-turbo

phrases related to performance or skill assessment

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

æ©Ł

-0.56

DCS

-0.52

Ħ¢

-0.52

ãĤ±

-0.47

AFP

-0.45

Dear

-0.45

ometown

-0.44

annabin

-0.44

cigarettes

-0.43

Wr

-0.43

POSITIVE LOGITS

 however

0.72

 though

0.63

tho

0.57

 meanwhile

0.56

nep

0.44

 moreover

0.43

 twitch

0.42

.")

0.40

 trusting

0.40

 ---------

0.39

Activations Density 3.763%

descriptions or reviews of various activities or items

phrases related to performance or skill assessment

No Comments

No Known Activations