INDEX

Explanations

phrases related to distance

oai_token-act-pair · gpt-3.5-turbo

references to distances or positions described as "away."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

xual

-0.78

ific

-0.76

elly

-0.70

 Zeit

-0.67

acus

-0.65

itious

-0.63

imony

-0.62

milo

-0.60

psons

-0.60

ouf

-0.60

POSITIVE LOGITS

hesda

0.73

bies

0.71

fitted

0.68

RAG

0.68

 "$:/

0.67

doors

0.67

fits

0.67

 Territories

0.66

ADRA

0.66

away

0.66

Activations Density 0.021%

phrases related to distance

references to distances or positions described as "away."

No Comments

No Known Activations