INDEX

Explanations

expressions related to holding law enforcement accountable

oai_token-act-pair · gpt-3.5-turbo

references to right-wing ideologies or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Plum

-0.70

 Noir

-0.65

KH

-0.63

 Vaughn

-0.62

 Guru

-0.61

 Solitaire

-0.60

 Pell

-0.60

Moj

-0.59

 Contest

-0.58

 Chill

-0.58

POSITIVE LOGITS

hander

1.28

handed

1.23

leaning

1.22

wing

1.21

angled

1.09

aligned

1.08

sided

1.08

thinking

1.07

hand

1.05

click

1.01

Activations Density 0.027%

expressions related to holding law enforcement accountable

references to right-wing ideologies or groups

No Comments

No Known Activations