INDEX

Explanations

adjectives emphasizing a moderate degree or level

oai_token-act-pair · gpt-3.5-turbo

instances of the word "moderate" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

tyard

-0.77

kefeller

-0.73

ilage

-0.73

 Chase

-0.71

arium

-0.70

inates

-0.65

ynthesis

-0.64

ledge

-0.64

stals

-0.64

tz

-0.63

POSITIVE LOGITS

erate

0.95

 minded

0.91

xual

0.87

 sized

0.85

(<

0.76

moderate

0.75

escal

0.67

er

0.66

minded

0.66

weights

0.64

Activations Density 0.041%

adjectives emphasizing a moderate degree or level

instances of the word "moderate" and its variations

No Comments

No Known Activations