INDEX

Explanations

numerical values and references related to competitive results or scores

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

@"/

-0.53

ära

-0.48

ciles

-0.48

icylic

-0.48

出版年

-0.47

 Lagu

-0.46

 base

-0.46

Win

-0.46

vă

-0.46

Extern

-0.46

POSITIVE LOGITS

Geplaatst

0.70

ScopeManager

0.65

ErrorListener

0.59

IntentFilter

0.56

Portale

0.56

TypedDataSet

0.55

richTextPanel

0.55

AlterField

0.52

yntaxException

0.52

 informée

0.51

Activations Density 0.006%

numerical values and references related to competitive results or scores

No Comments

No Known Activations