INDEX

Explanations

phrases that indicate a partial explanation or reason for something

oai_token-act-pair · gpt-3.5-turbo

references to contributions or components of various subjects

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

avorite

-0.74

pes

-0.66

onut

-0.66

iversal

-0.65

kefeller

-0.64

ishops

-0.64

 nodd

-0.63

lict

-0.63

 warriors

-0.63

soever

-0.62

POSITIVE LOGITS

PsyNetMessage

0.73

meier

0.69

 guiActiveUn

0.68

displayText

0.68

lie

0.65

meal

0.65

 Hess

0.64

ners

0.62

 è£ıè

0.61

SourceFile

0.59

Activations Density 0.019%

phrases that indicate a partial explanation or reason for something

references to contributions or components of various subjects

No Comments

No Known Activations