INDEX

Explanations

places and locations

oai_token-act-pair · gpt-3.5-turbo

mentions of geographic locations or entities related to specific places

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

 Niet

-0.66

anwhile

-0.63

enegger

-0.61

mble

-0.58

 referen

-0.53

milo

-0.52

hement

-0.51

eatures

-0.51

aminer

-0.50

wagen

-0.49

POSITIVE LOGITS

's

0.56

igon

0.48

rock

0.48

 soil

0.47

 County

0.46

 lately

0.44

 Avenue

0.44

 Zombies

0.44

Coin

0.43

gress

0.43

Activations Density 0.593%

places and locations

mentions of geographic locations or entities related to specific places

No Comments

No Known Activations