INDEX

Explanations

phrases where an object or concept is physically connected or attached to something else

oai_token-act-pair · gpt-3.5-turbo

instances of phrases indicating attachment or association

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

esi

-0.73

RD

-0.72

urg

-0.71

incinn

-0.70

TPPStreamerBot

-0.68

emetery

-0.68

Champ

-0.66

anchester

-0.65

hur

-0.65

orders

-0.65

POSITIVE LOGITS

othy

0.80

 handle

0.72

ggles

0.71

 conserve

0.71

 compensate

0.71

 shore

0.71

 preserve

0.70

 ensure

0.69

 insure

0.69

ffee

0.69

Activations Density 0.165%

phrases where an object or concept is physically connected or attached to something else

instances of phrases indicating attachment or association

No Comments

No Known Activations