INDEX

Explanations

phrases related to actions or processes that involve physical interaction or manipulation

oai_token-act-pair · gpt-3.5-turbo

verbs and actions associated with legal and procedural contexts

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

ãĤ´ãĥ³

-0.60

anwhile

-0.55

luster

-0.52

 Vaugh

-0.50

eatures

-0.50

TBA

-0.48

amara

-0.47

ä»£

-0.46

srf

-0.45

hetti

-0.45

POSITIVE LOGITS

igate

0.61

him

0.61

 oneself

0.61

 them

0.59

ulate

0.59

uggle

0.56

 your

0.56

ify

0.55

uate

0.54

urate

0.53

Activations Density 0.694%

phrases related to actions or processes that involve physical interaction or manipulation

verbs and actions associated with legal and procedural contexts

No Comments

No Known Activations