INDEX

Explanations

references to individual names, possibly related to political figures or entities

oai_token-act-pair · gpt-3.5-turbo

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

 idols

-0.83

 Heard

-0.71

 Idol

-0.70

 modesty

-0.69

 idol

-0.67

 McDonnell

-0.67

çīĪ

-0.67

Io

-0.62

KN

-0.62

ortium

-0.60

POSITIVE LOGITS

ller

0.97

kees

0.93

zon

0.93

llers

0.90

hest

0.89

quet

0.87

¶

0.86

ques

0.86

lling

0.85

boats

0.83

Activations Density 0.108%

references to individual names, possibly related to political figures or entities

No Comments

No Known Activations