INDEX

Explanations

proper nouns and quotations in a text

oai_token-act-pair · gpt-3.5-turbo

statements made by officials or authoritative figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 ordinances

-0.77

 neighbors

-0.75

 subdiv

-0.74

 Bigfoot

-0.72

dye

-0.71

 Craigslist

-0.71

 someday

-0.71

 sucker

-0.71

 numbering

-0.68

 zoning

-0.67

POSITIVE LOGITS

kish

0.93

onse

0.93

Speaking

0.86

 emphas

0.85

Foreign

0.80

 stressing

0.80

plom

0.78

ofi

0.75

inational

0.75

íķ

0.74

Activations Density 0.484%

proper nouns and quotations in a text

statements made by officials or authoritative figures

No Comments

No Known Activations