INDEX

Explanations

sequences of punctuation marks and their surrounding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

:\\

-0.72



-0.69

**/

-0.69



-0.65

「

-0.65

**/

-0.65

 "));

-0.65



-0.64

//

-0.63

</b>

-0.63

POSITIVE LOGITS

<em>

2.48

<i>

1.94

/*

1.19

/*

1.02

0.89

textit

0.72

 AssemblyCulture

0.72

《

0.71

+/*

0.69

makeConstraints

0.64

Activations Density 0.772%

sequences of punctuation marks and their surrounding contexts

No Comments

No Known Activations