INDEX

Explanations

the beginning of a new section or topic in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 "..\..\

-0.59

PreferredItem

-0.59

 house

-0.59

con

-0.58

 multiple

-0.58

 real

-0.57

kon

-0.57

berd

-0.54

uskas

-0.53

par

-0.53

POSITIVE LOGITS

})*/

0.84

 CURIAM

0.82

Referanser

0.80

\{\\

0.74

<tfoot>

0.74

 itſelf

0.73

 myſelf

0.71

tvguidetime

0.71

*/}

0.70

 fevere

0.69

Activations Density 0.023%

the beginning of a new section or topic in a document

No Comments

No Known Activations