INDEX

Explanations

authors and their collaborators

oai_token-act-pair · gpt-3.5-turbo

references to academic citations and authors in research documents

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

FactoryReloaded

-0.75

 Username

-0.74

 comprom

-0.73

 Maker

-0.70

 Shades

-0.68

ropolitan

-0.68

 Corps

-0.63

Ner

-0.62

lift

-0.62

lif

-0.61

POSITIVE LOGITS

.,

1.16

abo

0.81

ibi

0.81

.,"

0.79

rador

0.79

herty

0.78

ibaba

0.77

idents

0.74

axter

0.74

aeda

0.74

Activations Density 0.022%

authors and their collaborators

references to academic citations and authors in research documents

No Comments

No Known Activations