INDEX

Explanations

keywords related to opting out, unsubscribe, and agreement clauses

oai_token-act-pair · gpt-3.5-turbo

phrases related to opting out or unsubscribing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Invention

-0.70

ateurs

-0.60

 Barber

-0.56

Lau

-0.55

enegger

-0.55

 Instruct

-0.55

 shortages

-0.54

 Cran

-0.54

 Hits

-0.53

 Berger

-0.53

POSITIVE LOGITS

renheit

0.82

 subscribing

0.80

xon

0.75

 anytime

0.72

 captcha

0.71

antha

0.69

 "$:/

0.67

dinand

0.66

anyl

0.65

Activations Density 0.031%

keywords related to opting out, unsubscribe, and agreement clauses

phrases related to opting out or unsubscribing

No Comments

No Known Activations