INDEX

Explanations

verbs indicating actions or decisions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating rules or obligations within a legal or regulatory context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

weed

-0.44

azo

-0.41

UFC

-0.41

boo

-0.40

 algae

-0.39

 sunscreen

-0.38

pic

-0.38

ALS

-0.37

 kids

-0.37

 selfie

-0.37

POSITIVE LOGITS

 moreover

0.49

etheless

0.48

 scholars

0.47

 scholar

0.47

itud

0.46

 historian

0.45

minist

0.45

ĸļ

0.45

 neocons

0.44

 foremost

0.44

Activations Density 2.179%

verbs indicating actions or decisions

phrases indicating rules or obligations within a legal or regulatory context

No Comments

No Known Activations