INDEX

Explanations

people's names

oai_token-act-pair · gpt-3.5-turbo

titles and names associated with films and notable works

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

reau

-0.90

ufact

-0.76

ovie

-0.54

imeters

-0.54

otaur

-0.54

leneck

-0.53

etooth

-0.53

 crunch

-0.53

 centr

-0.52

 GOODMAN

-0.52

POSITIVE LOGITS

å£«

0.70

Wid

0.57

 reven

0.56

ayn

0.53

 Herald

0.53

utsche

0.52

URR

0.51

missions

0.50

 Judgment

0.50

ĸļ

0.50

Activations Density 1.129%

people's names

titles and names associated with films and notable works

No Comments

No Known Activations