INDEX

Explanations

phrases indicating the start or beginning of something

oai_token-act-pair · gpt-3.5-turbo

instances of beginnings or initial phases of topics or events

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

ult

-0.75

inance

-0.71

acha

-0.70

sleep

-0.69

atography

-0.68

ophon

-0.68

luaj

-0.67

elo

-0.66

leigh

-0.65

isl

-0.64

POSITIVE LOGITS

-->

0.80

 scratching

0.78

 scratches

0.76

 frontier

0.72

 collateral

0.71

 sympt

0.71

 stim

0.66

 scratched

0.65

 consolation

0.65

Gate

0.64

Activations Density 0.162%

phrases indicating the start or beginning of something

instances of beginnings or initial phases of topics or events

No Comments

No Known Activations