INDEX

Explanations

proper nouns related to geographical locations, specifically places in LA

oai_token-act-pair · gpt-3.5-turbo

mentions of Los Angeles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

é¾įå¥ĳå£«

-0.75

lers

-0.71

ãĥĥãĥĪ

-0.70

stroke

-0.70

panic

-0.68

framework

-0.68

deck

-0.68

milo

-0.68

addons

-0.66

posts

-0.65

POSITIVE LOGITS

UNCH

1.15

uthor

0.99

UGH

0.93

IRE

0.88

KE

0.85

velength

0.85

 Lumpur

0.82

LA

0.79

OPS

0.78

izabeth

0.77

Activations Density 0.003%

proper nouns related to geographical locations, specifically places in LA

mentions of Los Angeles

No Comments

No Known Activations