INDEX

Explanations

references to individuals associated with specific organizations

oai_token-act-pair · gpt-3.5-turbo

references to authoritative figures or experts in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

stood

-0.53

abiding

-0.51

 wagon

-0.50

awa

-0.48

 semblance

-0.46

ardless

-0.46

 chilling

-0.46

given

-0.45

 requisite

-0.45

 selves

-0.45

POSITIVE LOGITS

 Higher

0.61

 Research

0.58

 Strategies

0.58

Media

0.56

ipl

0.56

 Securities

0.56

 Education

0.55

Bio

0.54

 Intelligence

0.53

Lia

0.53

Activations Density 1.598%

references to individuals associated with specific organizations

references to authoritative figures or experts in various fields

No Comments

No Known Activations