INDEX

Explanations

keywords related to research findings and reports

oai_token-act-pair · gpt-3.5-turbo

references to research findings and their implications

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

oned

-0.68

 chopping

-0.68

oning

-0.65

tz

-0.64

osi

-0.64

mph

-0.63

bid

-0.63

 routes

-0.63

onement

-0.62

 monop

-0.61

POSITIVE LOGITS

iveness

1.03

 findings

0.93

ĸļ

0.75

ivist

0.74

DragonMagazine

0.73

~~~~~~~~~~~~~~~~

0.73

uggest

0.72

ãĥĻ

0.72

itutional

0.70

iments

0.70

Activations Density 0.037%

keywords related to research findings and reports

references to research findings and their implications

No Comments

No Known Activations