INDEX

Explanations

proper nouns such as names of companies and individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific organizations or groups

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

 increments

-0.70

 retri

-0.67

orgetown

-0.67

 POLITICO

-0.67

 mater

-0.66

cum

-0.63

 Trayvon

-0.59

 Lear

-0.57

Democrats

-0.57

 lawmakers

-0.57

POSITIVE LOGITS

 themselves

1.05

senal

0.94

 logo

0.76

 organise

0.75

 mascot

0.73

 kindly

0.72

ç¥ŀ

0.71

 wisely

0.70

HQ

0.69

camp

0.67

Activations Density 1.118%

proper nouns such as names of companies and individuals

mentions of specific organizations or groups

No Comments

No Known Activations