INDEX

Explanations

instances of the word "program"

oai_token-act-pair · gpt-3.5-turbo

references to programs or initiatives

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

pick

-0.74

 dilig

-0.73

 Robots

-0.68

picking

-0.65

âĶĢâĶĢâĶĢâĶĢ

-0.64

poll

-0.64

uple

-0.62

ModLoader

-0.62

SO

-0.62

Pick

-0.61

POSITIVE LOGITS

mable

2.12

matic

1.69

matically

1.68

mers

1.19

mes

1.12

atically

1.00

ming

0.99

matical

0.95

atical

0.95

 Gutenberg

0.93

Activations Density 0.049%

instances of the word "program"

references to programs or initiatives

No Comments

No Known Activations