INDEX

Explanations

phrases related to physical objects, structures, or locations with the term "bed".

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "bed."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

artifacts

-0.74

 nomine

-0.72

phies

-0.66

 taxable

-0.66

 contrace

-0.66

abeth

-0.65

 offsets

-0.64

£ı

-0.64

 pancakes

-0.62

qqa

-0.62

POSITIVE LOGITS

ding

1.19

ded

1.08

dit

1.00

bed

0.95

ford

0.95

bing

0.89

acles

0.82

rock

0.80

rill

0.80

nik

0.79

Activations Density 0.013%

phrases related to physical objects, structures, or locations with the term "bed".

occurrences of the term "bed."

No Comments

No Known Activations