INDEX

Explanations

special formatting or markup within the text, possibly indicating sections or important elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

DeleteBehavior

-0.75

SharedDtor

-0.71

ContentAsync

-0.71

 &___

-0.70

日閲覧

-0.69

ніципалі

-0.69

DoubleQuotes

-0.69

msgTypes

-0.69

sizeCache

-0.68

@"/

-0.68

POSITIVE LOGITS

 createSlice

0.53

 makeStyles

0.48

 Fauci

0.48

">//

0.46

 Nema

0.45

λέον

0.45

InstrumentedTest

0.43

 inuti

0.42

Ξ

0.42

Segoe

0.41

Activations Density 0.020%

special formatting or markup within the text, possibly indicating sections or important elements

No Comments

No Known Activations