INDEX

Explanations

phrases or sentences with the word "attributed" followed by a high activation number

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of attribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

lake

-0.74

lite

-0.71

thin

-0.69

cre

-0.67

astern

-0.65

cum

-0.62

 Fusion

-0.62

 Stras

-0.60

ben

-0.59

 Sandwich

-0.59

POSITIVE LOGITS

 attribut

1.09

 attributed

1.01

 corrid

0.97

 attribution

0.89

 acknow

0.87

 unden

0.83

 blame

0.83

 misunder

0.82

inished

0.80

 conclud

0.76

Activations Density 0.008%

phrases or sentences with the word "attributed" followed by a high activation number

words related to the concept of attribution

No Comments

No Known Activations