INDEX

Explanations

numerical references in the format of section numbers and codes

oai_token-act-pair · gpt-3.5-turbo

references to tax-related classifications and organizations

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

anguage

-0.81

lock

-0.75

anguages

-0.74

onen

-0.73

skirts

-0.70

 Dynam

-0.68

voy

-0.68

 Languages

-0.66

locks

-0.66

lain

-0.64

POSITIVE LOGITS

exempt

0.78

 nonprofit

0.76

 nonprofits

0.72

 Investor

0.70

affiliated

0.69

 charitable

0.67

ledged

0.66

 Benef

0.65

ERAL

0.65

0.64

Activations Density 0.082%

numerical references in the format of section numbers and codes

references to tax-related classifications and organizations

No Comments

No Known Activations