INDEX

Explanations

phrases related to extremist political views, movements, and groups

oai_token-act-pair · gpt-3.5-turbo

terms associated with extremist political ideologies, particularly those on the far right

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

ĸļ

-0.90

 captcha

-0.78

 Amph

-0.73

Yon

-0.72

 CrossRef

-0.69

 Dragonbound

-0.69

 Siem

-0.68

 Guan

-0.67

Cue

-0.67

HM

-0.67

POSITIVE LOGITS

 extremist

1.25

acists

1.22

 extremists

1.20

acist

1.20

Islam

1.16

fascist

1.15

ists

1.14

 nationalist

1.13

femin

1.13

Democrats

1.12

Activations Density 0.348%

phrases related to extremist political views, movements, and groups

terms associated with extremist political ideologies, particularly those on the far right

No Comments

No Known Activations