INDEX

Explanations

mentions of protection, concern for well-being, and potential risks to individuals or groups

oai_token-act-pair · gpt-3.5-turbo

references to the lives and wellbeing of individuals or groups within society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

NetMessage

-0.73

wcsstore

-0.73

©¶æ¥µ

-0.71

adan

-0.71

ÅĤ

-0.71

cano

-0.69

ritis

-0.69

etsk

-0.68

ocations

-0.67

amb

-0.66

POSITIVE LOGITS

 individuals

0.83

 those

0.78

 sorts

0.71

 course

0.70

 citizens

0.69

 others

0.69

 Nations

0.68

 ordinary

0.67

 Individuals

0.66

icial

0.65

Activations Density 0.249%

mentions of protection, concern for well-being, and potential risks to individuals or groups

references to the lives and wellbeing of individuals or groups within society

No Comments

No Known Activations