INDEX

Explanations

phrases related to travel or transportation, such as buying tickets and getting on trains

oai_token-act-pair · gpt-3.5-turbo

periods and sentence endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

wom

-0.75

atre

-0.73

 Nasa

-0.68

 Sisters

-0.67

 creeping

-0.62

WOM

-0.62

 downs

-0.61

 Warp

-0.61

 Down

-0.61

 flavours

-0.60

POSITIVE LOGITS

orius

0.71

©¶æ¥µ

0.70

monary

0.68

resources

0.67

property

0.66

utive

0.66

displayText

0.65

atten

0.64

 reserves

0.64

member

0.64

Activations Density 0.000%

phrases related to travel or transportation, such as buying tickets and getting on trains

periods and sentence endings

No Comments

No Known Activations