INDEX

Explanations

titles or headings within text

oai_token-act-pair · gpt-3.5-turbo

specific titles of works or projects

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

leans

-0.74

stood

-0.70

ĪĴ

-0.70

pora

-0.69

Benz

-0.66

 Chambers

-0.64

Gam

-0.64

nikov

-0.63

 unsus

-0.62

ministic

-0.62

POSITIVE LOGITS

widget

0.84

 caption

0.83

 Featured

0.78

 toggle

0.78

][/

0.77

 Thumbnails

0.75

url

0.75

Enlarge

0.74

toggle

0.74

 embed

0.74

Activations Density 0.144%

titles or headings within text

specific titles of works or projects

No Comments

No Known Activations