INDEX

Explanations

words related to stickers or price tags

oai_token-act-pair · gpt-3.5-turbo

references to stickers

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

ernandez

-0.89

icz

-0.81

ITNESS

-0.78

scill

-0.75

acan

-0.74

iggurat

-0.74

ahime

-0.73

Ago

-0.73

apor

-0.73

asca

-0.73

POSITIVE LOGITS

 stickers

1.31

 sticker

1.21

 sheet

0.95

holders

0.90

 sheets

0.83

 markings

0.81

holder

0.81

 stripe

0.81

raft

0.79

sheet

0.76

Activations Density 0.020%

words related to stickers or price tags

references to stickers

No Comments

No Known Activations