INDEX

Explanations

proper nouns, specifically locations or names of places and people

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or landmarks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eat

-0.78

elling

-0.76

arial

-0.73

elled

-0.72

el

-0.72

isp

-0.72

oiler

-0.70

etime

-0.70

redd

-0.70

olkien

-0.70

POSITIVE LOGITS

 Pioneer

1.21

 Woman

0.80

 Village

0.76

 Commercial

0.76

 Square

0.75

é¾įå¥ĳå£«

0.73

conservancy

0.73

asus

0.73

heny

0.73

sonian

0.72

Activations Density 0.017%

proper nouns, specifically locations or names of places and people

references to specific locations or landmarks

No Comments

No Known Activations