INDEX

Explanations

references to political ideologies or movements associated with the term "neo."

oai_token-act-pair · gpt-3.5-turbo

references to neo-Nazi ideology and groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 ILCS

-0.89

ORED

-0.80

ãĤ¼ãĤ¦ãĤ¹

-0.79

Interstitial

-0.79

loo

-0.79

hips

-0.79

worthiness

-0.77

channelAvailability

-0.77

lessly

-0.73

ULL

-0.72

POSITIVE LOGITS

ge

0.95

neo

0.76

flex

0.75

emer

0.73

azi

0.73

fer

0.73

chal

0.71

 mascul

0.70

fascist

0.69

Activations Density 0.009%

references to political ideologies or movements associated with the term "neo."

references to neo-Nazi ideology and groups

No Comments

No Known Activations