INDEX

Explanations

phrases indicating admission of an action or fact by someone

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "admit" and its derivatives

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

intosh

-0.76

edged

-0.73

emort

-0.71

patch

-0.69

footed

-0.69

leground

-0.68

headed

-0.67

ridges

-0.66

headers

-0.64

back

-0.63

POSITIVE LOGITS

ilet

0.77

 srfAttach

0.74

asted

0.71

ggles

0.70

asting

0.68

 recreate

0.68

 satisfy

0.64

esty

0.64

YS

0.62

 embody

0.61

Activations Density 0.058%

phrases indicating admission of an action or fact by someone

instances of the verb "admit" and its derivatives

No Comments

No Known Activations