INDEX

Explanations

statements related to expertise or the mention of an expert in various fields

oai_token-act-pair · gpt-3.5-turbo

references to expertise or expert opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Helsinki

-0.66

MET

-0.62

à¥

-0.62

 Territories

-0.61

FACE

-0.61

DEP

-0.61

apo

-0.61

forth

-0.60

 Pesh

-0.60

 Kand

-0.60

POSITIVE LOGITS

sonian

1.11

ulously

0.94

minded

0.83

icion

0.81

ommel

0.81

 opinion

0.79

 reviewer

0.78

 endors

0.75

inent

0.74

 guiActiveUn

0.73

Activations Density 0.019%

statements related to expertise or the mention of an expert in various fields

references to expertise or expert opinions

No Comments

No Known Activations