INDEX

Explanations

verbs related to performing actions or operations

oai_token-act-pair · gpt-3.5-turbo

the end of the document

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

wives

-0.56

ãĥ¼ãĥĨ

-0.54

Tokens

-0.53

itri

-0.53

thing

-0.52

gins

-0.50

argon

-0.50

rone

-0.49

 Koreans

-0.48

âĹ¼

-0.48

POSITIVE LOGITS

ometimes

0.70

 sqor

0.69

ource

0.69

heet

0.66

hift

0.66

paces

0.65

olation

0.63

pace

0.63

CRIPTION

0.62

PORT

0.62

Activations Density 0.293%

verbs related to performing actions or operations

the end of the document

No Comments

No Known Activations