INDEX

Explanations

mentions of advertisements in a text

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "advertisement."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

clud

-0.71

come

-0.70

tein

-0.70

heed

-0.70

 honour

-0.67

erva

-0.66

 honor

-0.64

iency

-0.64

ologically

-0.64

itialized

-0.64

POSITIVE LOGITS

 Advertisement

1.08

 Thumbnails

0.92

 advertisement

0.89

 Transcript

0.85

culosis

0.83

Interstitial

0.79

Skip

0.76

iban

0.73

advertisement

0.73

Ads

0.73

Activations Density 0.003%

mentions of advertisements in a text

occurrences of the word "advertisement."

No Comments

No Known Activations