INDEX

Explanations

mentions of specific locations, especially cities

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ments

-0.83

htaking

-0.81

ramer

-0.79

ontent

-0.76

comed

-0.75

tale

-0.73

rav

-0.73

isive

-0.72

region

-0.71

nut

-0.70

POSITIVE LOGITS

vous

0.79

ito

0.71

alez

0.66

--+

0.65

 Corpus

0.64

Bee

0.64

 Mercury

0.64

Od

0.63

 Jinn

0.62

 Perez

0.62

Activations Density 0.072%

mentions of specific locations, especially cities

proper nouns and specific names

No Comments

No Known Activations