INDEX

Explanations

references to articles

oai_token-act-pair · gpt-3.5-turbo

instances of the word "article."

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

selves

-0.79

Ĭ±

-0.71

 Governors

-0.69

Lens

-0.65

Tokens

-0.64

Calling

-0.63

Magikarp

-0.62

 Sleeping

-0.61

 Cases

-0.59

 Genie

-0.59

POSITIVE LOGITS

 contains

1.23

 summarizes

1.16

 assumes

1.14

 represents

1.13

 illustrates

1.02

 provides

1.00

is

0.99

 reflects

0.98

 includes

0.97

 relies

0.97

Activations Density 0.114%

references to articles

instances of the word "article."

No Comments

No Known Activations