INDEX

Explanations

phrases that indicate a connection or link between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate relationships or connections between concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ocker

-0.65

UFF

-0.62

Fan

-0.58

Forest

-0.58

ocaust

-0.57

DIS

-0.56

ifter

-0.56

zan

-0.56

owe

-0.55

cre

-0.55

POSITIVE LOGITS

 thereto

1.02

 intimately

0.86

 geographically

0.85

to

0.80

 closely

0.77

ences

0.76

icut

0.75

ivalent

0.75

 intrinsically

0.73

linked

0.71

Activations Density 0.130%

phrases that indicate a connection or link between different entities or concepts

phrases that indicate relationships or connections between concepts or entities

No Comments

No Known Activations