INDEX

Explanations

people or entities being eliminated or eradicated

oai_token-act-pair · gpt-3.5-turbo

phrases related to destruction or elimination

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

anooga

-0.85

egal

-0.85

ensical

-0.84

fman

-0.81

pheus

-0.79

ruciating

-0.73

equal

-0.70

heid

-0.69

ItemThumbnailImage

-0.69

annis

-0.69

POSITIVE LOGITS

 wiping

0.87

 wipe

0.85

 goodbye

0.79

down

0.77

 wipes

0.73

downs

0.73

 wiped

0.72

stakes

0.72

 erase

0.72

 slate

0.71

Activations Density 0.026%

people or entities being eliminated or eradicated

phrases related to destruction or elimination

No Comments

No Known Activations