INDEX

Explanations

phrases mentioning medical conditions or procedures

oai_token-act-pair · gpt-3.5-turbo

references to specific years, events, or affiliations in a historical context

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

 signalling

-0.64

yip

-0.60

INTON

-0.58

 tide

-0.56

 cents

-0.56

hed

-0.55

 blindly

-0.54

 source

-0.53

ocating

-0.53

 carriers

-0.53

POSITIVE LOGITS

sic

0.86

pmwiki

0.71

SPONSORED

0.69

ryu

0.69

ibrary

0.66

£ı

0.64

etheless

0.63

 Sicily

0.62

Downloadha

0.62

ttes

0.62

Activations Density 1.258%

phrases mentioning medical conditions or procedures

references to specific years, events, or affiliations in a historical context

No Comments

No Known Activations