INDEX

Explanations

multiword phrases containing "anti-" prefixes

oai_token-act-pair · gpt-3.5-turbo

phrases related to anti-government or anti-establishment sentiments

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

swick

-0.82

çīĪ

-0.77

ulhu

-0.75

ĸļ

-0.75

ADRA

-0.73

 Brist

-0.72

WD

-0.69

 Nieto

-0.68

 Barron

-0.67

Zup

-0.67

POSITIVE LOGITS

establishment

1.10

government

1.08

social

1.08

Semitic

1.03

competitive

1.02

commun

1.00

gravity

0.96

human

0.95

violence

0.95

discrimination

0.93

Activations Density 0.044%

multiword phrases containing "anti-" prefixes

phrases related to anti-government or anti-establishment sentiments

No Comments

No Known Activations