INDEX

Explanations

references to laws, regulations, and forms of enforcement as well as actions emphasizing accountability

oai_token-act-pair · gpt-3.5-turbo

references to addiction-related behaviors and societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 nutshell

-0.78

 Collider

-0.63

phe

-0.60

 Canaver

-0.60

 hindsight

-0.59

ensional

-0.59

erest

-0.58

 congr

-0.58

enario

-0.57

 magnitude

-0.57

POSITIVE LOGITS

etc

0.83

 meals

0.69

 accordingly

0.69

 medicines

0.67

 nearby

0.66

 ambul

0.65

 punishments

0.65

soever

0.65

 pornographic

0.65

 cafes

0.62

Activations Density 0.936%

references to laws, regulations, and forms of enforcement as well as actions emphasizing accountability

references to addiction-related behaviors and societal issues

No Comments

No Known Activations