INDEX

Explanations

phrases related to military or conflict operations

oai_token-act-pair · gpt-3.5-turbo

words and phrases associated with various "can" forms and the concept of capability or ability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

RESULTS

-0.76

anwhile

-0.69

 pestic

-0.69

endi

-0.64

kefeller

-0.62

Thumbnail

-0.61

jri

-0.60

ansson

-0.58

 ingred

-0.58

olicy

-0.57

POSITIVE LOGITS

rike

0.58

arching

0.56

 unfocusedRange

0.56

©¶æ

0.54

 Tradable

0.54

ictionary

0.52

numbered

0.51

tower

0.50

cation

0.49

ŃĶ

0.48

Activations Density 6.321%

phrases related to military or conflict operations

words and phrases associated with various "can" forms and the concept of capability or ability

No Comments

No Known Activations