INDEX

Explanations

advertisements within the text

oai_token-act-pair · gpt-3.5-turbo

instances of advertisement or promotional content

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĪĴ

-0.78

 espionage

-0.63

erness

-0.63

 determination

-0.61

 deduct

-0.60

 idol

-0.59

 diffusion

-0.59

 hinges

-0.59

 arms

-0.59

 benches

-0.57

POSITIVE LOGITS

advertisement

0.89

é¾įå

0.79

 Continue

0.77

RELATED

0.72

adish

0.70

 VIDEOS

0.69

Î½

0.67

æ©Ł

0.67

Featured

0.67

Ep

0.67

Activations Density 0.037%

advertisements within the text

instances of advertisement or promotional content

No Comments

No Known Activations