INDEX

Explanations

mentions of the letter "H" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kloped

-0.88

astify

-0.83

 ―――――

-0.82

 externi

-0.82

BibitemShut

-0.81

 doubtnut

-0.80

 myſelf

-0.80

قایناق‌لار

-0.78

SourceChecksum

-0.76

 ſind

-0.74

POSITIVE LOGITS

3.76

3.38

2.36

setH

1.95

1.93

Ｈ

1.61

ه

1.40

ह

1.25

Х

1.20

rH

1.19

Activations Density 0.165%

mentions of the letter "H" in various contexts

No Comments

No Known Activations