INDEX

Explanations

proper nouns related to people and locations

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals with the name Nguyen and references to Cambodia

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

tered

-0.80

BIP

-0.78

rael

-0.78

IELD

-0.78

BALL

-0.74

gered

-0.72

cano

-0.71

HEAD

-0.70

espie

-0.69

PUT

-0.69

POSITIVE LOGITS

 Nguyen

1.26

 Cambod

0.94

 Cambodia

0.84

guyen

0.84

itton

0.84

 Vietnamese

0.82

Hua

0.81

Sov

0.77

ongs

0.75

 Laos

0.74

Activations Density 0.026%

proper nouns related to people and locations

mentions of individuals with the name Nguyen and references to Cambodia

No Comments

No Known Activations