INDEX

Explanations

terms related to granularity and granules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

registrer

-0.59

️

-0.58

ImageContext

-0.56

 Nerven

-0.54

="/">

-0.54

stylers

-0.54

 trots

-0.54

 Nunn

-0.52

Xoa

-0.52

dings

-0.52

POSITIVE LOGITS

gran

0.68

 يتيمه

0.66

 ThemeData

0.64

 Gran

0.63

 gran

0.63

Gran

0.62

లాలు

0.61

__":

0.61

 granny

0.60

 GRAN

0.60

Activations Density 0.169%

terms related to granularity and granules

No Comments

No Known Activations