INDEX

Explanations

the word 'wipe' or related terms

oai_token-act-pair · gpt-3.5-turbo

phrases involving the concept of wiping out or eradicating something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

fman

-0.89

ensical

-0.83

ruciating

-0.82

anooga

-0.77

egal

-0.76

yrinth

-0.74

pheus

-0.74

 guiActiveUnfocused

-0.73

entanyl

-0.72

equal

-0.70

POSITIVE LOGITS

 wiping

0.85

 wipes

0.84

 wipe

0.83

down

0.77

 wiped

0.76

 slate

0.74

downs

0.74

stakes

0.73

 goodbye

0.73

brush

0.73

Activations Density 0.040%

the word 'wipe' or related terms

phrases involving the concept of wiping out or eradicating something

No Comments

No Known Activations