INDEX

Explanations

references to the name "Kate" in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Kate"

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

ATIONS

-0.89

atio

-0.87

indal

-0.76

ATIVE

-0.75

ations

-0.72

 externalToEVAOnly

-0.70

iple

-0.70

ensical

-0.69

ENSE

-0.69

ATOR

-0.68

POSITIVE LOGITS

 Upton

1.02

vich

0.93

 Wins

0.89

lyn

0.87

patrick

0.82

 Moss

0.82

 Mara

0.79

hi

0.78

rina

0.78

vic

0.78

Activations Density 0.038%

references to the name "Kate" in the text

mentions of the name "Kate"

No Comments

No Known Activations