INDEX

Explanations

phrases indicating the action of getting rid of something

oai_token-act-pair · gpt-3.5-turbo

phrases related to eliminating or removing items or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mpeg

-0.66

ORD

-0.65

BuyableInstoreAndOnline

-0.64

 Immortal

-0.64

anwhile

-0.64

NZ

-0.63

KEN

-0.63

OD

-0.62

STAT

-0.62

OLD

-0.61

POSITIVE LOGITS

ged

0.93

anium

0.90

ges

0.89

icide

0.83

ients

0.83

itaire

0.83

baugh

0.83

uations

0.83

icides

0.80

osaurus

0.80

Activations Density 0.012%

phrases indicating the action of getting rid of something

phrases related to eliminating or removing items or issues

No Comments

No Known Activations