INDEX

Explanations

proper nouns related to specific geographical locations

oai_token-act-pair · gpt-3.5-turbo

geographical locations and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Afee

-0.83

pter

-0.78

ãĤ¨ãĥ«

-0.77

lihood

-0.75

ãĥĦ

-0.75

ographed

-0.73

Tok

-0.70

 reper

-0.69

 Hiroshima

-0.68

idious

-0.68

POSITIVE LOGITS

 provincial

0.91

 Government

0.89

 Highlands

0.89

 Rural

0.88

 Governments

0.87

 Provincial

0.86

 governments

0.86

 legislatures

0.86

 Unemployment

0.86

 legislature

0.84

Activations Density 0.061%

proper nouns related to specific geographical locations

geographical locations and names

No Comments

No Known Activations