INDEX

Explanations

passive and action-related phrases

oai_token-act-pair · gpt-3.5-turbo

content related to illegal activities or suspicious behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 lauded

-0.64

 pioneered

-0.63

 hailed

-0.58

 experimented

-0.57

 teased

-0.57

 roared

-0.57

 fascinated

-0.57

 reinvent

-0.56

 debuted

-0.55

 ventured

-0.54

POSITIVE LOGITS

sic

0.65

apes

0.65

ccess

0.63

burse

0.60

ratom

0.59

ļéĨĴ

0.58

apses

0.57

odan

0.57

uggle

0.56

orship

0.55

Activations Density 1.304%

passive and action-related phrases

content related to illegal activities or suspicious behavior

No Comments

No Known Activations