INDEX

Explanations

elements related to specific entities and classifications

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

auto, loan, claim, cycle

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

endphp

-0.71

 تانيه

-0.65

 CURIAM

-0.63

featureID

-0.60

 resourceCulture

-0.58

rawDesc

-0.54

قایناق‌لار

-0.54

躇

-0.54

 rhestr

-0.53

 jadx

-0.52

POSITIVE LOGITS

]")]

0.52

 Polskiego

0.44

 "..\..\..\

0.40

 paraître

0.38

 franz

0.38

 Politique

0.36

Composable

0.34

 SimpleName

0.33

 "..\..\

0.33

xFFFF

0.33

Activations Density 0.068%

elements related to specific entities and classifications

auto, loan, claim, cycle

No Comments

No Known Activations