INDEX

Explanations

mentions of specific names or entities in news articles

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals and entities

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

otine

-0.84

izations

-0.84

illian

-0.79

ivals

-0.79

ians

-0.76

urgy

-0.76

icked

-0.75

ais

-0.73

ous

-0.73

 Pengu

-0.72

POSITIVE LOGITS

Dee

1.00

pling

0.92

zie

0.89

bris

0.86

gradation

0.83

lde

0.82

ples

0.80

velop

0.78

plin

0.78

ble

0.77

Activations Density 0.043%

mentions of specific names or entities in news articles

proper nouns, specifically names of individuals and entities

No Comments

No Known Activations