INDEX

Explanations

phrases related to specific place names

oai_token-act-pair · gpt-3.5-turbo

references to environmental and ecological topics

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

ccording

-0.83

Ö¼

-0.71

Obj

-0.68

 looph

-0.68

hiba

-0.67

-+-+

-0.65

 conclud

-0.65

Minor

-0.64

Lenin

-0.64

ĳå£«

-0.63

POSITIVE LOGITS

tein

0.82

eers

0.74

0.69

 Garland

0.69

izons

0.67

deals

0.66

ifications

0.64

 Initiative

0.63

 initiatives

0.63

0.59

Activations Density 0.125%

phrases related to specific place names

references to environmental and ecological topics

No Comments

No Known Activations