INDEX

Explanations

numerical values or quantities mentioned in a document

oai_token-act-pair · gpt-3.5-turbo

comparisons and quantities expressed with "as" or similar phrasing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 secondly

-0.61

 obligation

-0.61

 additionally

-0.59

 whatsoever

-0.56

 unlaw

-0.56

IVES

-0.55

sworth

-0.54

smith

-0.54

ibl

-0.53

 Bros

-0.53

POSITIVE LOGITS

low

1.16

 high

1.05

low

1.03

phy

1.01

ym

0.99

little

0.98

 little

0.96

Low

0.90

ynchron

0.89

 much

0.88

Activations Density 0.100%

numerical values or quantities mentioned in a document

comparisons and quantities expressed with "as" or similar phrasing

No Comments

No Known Activations