INDEX

Explanations

prepositions indicating locations or positions

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

years in places

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 tatuagens

-0.42

 overras

-0.42

 cancelación

-0.40

 circonstances

-0.40

 segnal

-0.39

 cejas

-0.39

InjectMocks

-0.38

allowNull

-0.37

 forbindelse

-0.37

 réfrig

-0.37

POSITIVE LOGITS

 kasarigan

0.90

 AssemblyCulture

0.73

__":

0.66

ValueStyle

0.64

TypedDataSet

0.64

)";

0.63

Билгалдахарш

0.62

posedge

0.60

*/].

0.59

󠁣

0.59

Activations Density 0.022%

prepositions indicating locations or positions

years in places

No Comments

No Known Activations