INDEX

Explanations

specific locations or structured data formats

oai_token-act-pair · gpt-3.5-turbo

elements related to titles and naming conventions in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

SPONSORED

-0.71

akeru

-0.68

utra

-0.63

reau

-0.62

angelo

-0.60

BALL

-0.60

Äĩ

-0.59

ongyang

-0.58

gress

-0.57

CAP

-0.57

POSITIVE LOGITS

oxide

0.57

WHERE

0.56

hews

0.54

ffe

0.53

introdu

0.52

monds

0.52

ĸļ

0.50

ministic

0.50

atha

0.49

 corners

0.49

Activations Density 0.418%

specific locations or structured data formats

elements related to titles and naming conventions in various contexts

No Comments

No Known Activations