INDEX

Explanations

numerals and proper nouns

oai_token-act-pair · gpt-3.5-turbo

numerical values associated with places or events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wagen

-0.84

ses

-0.71

andowski

-0.70

 Blackwell

-0.65

 thereafter

-0.64

 thereto

-0.63

rogen

-0.63

ivil

-0.63

 likeness

-0.61

 policeman

-0.61

POSITIVE LOGITS

advertising

1.01

 Cosponsors

0.74

Population

0.70

Avg

0.70

ohyd

0.69

 Located

0.69

Year

0.67

Age

0.66

ãĤ¨ãĥ«

0.64

hester

0.64

Activations Density 0.248%

numerals and proper nouns

numerical values associated with places or events

No Comments

No Known Activations