INDEX

Explanations

advertisements and classified information

oai_token-act-pair · gpt-3.5-turbo

patterns related to advertisements and promotional content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

erness

-0.64

rency

-0.63

 elev

-0.60

 representative

-0.60

 bribery

-0.60

 secretaries

-0.60

Osw

-0.59

 determination

-0.59

milo

-0.59

tal

-0.57

POSITIVE LOGITS

advertisement

0.90

Î½

0.76

 Continue

0.75

é¾įå

0.73

Advertisement

0.70

embed

0.69

 VIDEOS

0.69

Featured

0.68

kr

0.66

 Thumbnails

0.66

Activations Density 0.040%

advertisements and classified information

patterns related to advertisements and promotional content

No Comments

No Known Activations