INDEX

Explanations

phrases related to description or characterization

oai_token-act-pair · gpt-3.5-turbo

phrases related to the act of describing or expressing something

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

 deposit

-0.68

cho

-0.63

 Encounter

-0.63

 deposits

-0.61

 contrace

-0.61

 undet

-0.61

esm

-0.60

 blockers

-0.59

 manned

-0.59

 bloc

-0.59

POSITIVE LOGITS

FontSize

1.08

soType

1.03

Quantity

0.86

Adapt

0.73

ãĤ¢ãĥ«

0.72

 understatement

0.71

ASON

0.69

SourceFile

0.69

Appearance

0.69

 descriptions

0.68

Activations Density 0.133%

phrases related to description or characterization

phrases related to the act of describing or expressing something

No Comments

No Known Activations