INDEX

Explanations

words related to different countries and regions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'u'

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 horizont

-0.85

=-=-

-0.74

*/(

-0.73

 Attribution

-0.72

 therap

-0.70

 SERV

-0.69

 Cosponsors

-0.68

 trave

-0.65

milo

-0.65

 constants

-0.65

POSITIVE LOGITS

pport

1.31

cca

1.17

ccess

1.09

uru

0.98

seless

0.97

pta

0.96

isine

0.95

cci

0.95

itton

0.95

ji

0.94

Activations Density 0.028%

words related to different countries and regions

occurrences of the letter 'u'

No Comments

No Known Activations