INDEX

Explanations

references to keywords and instructions for usage or description

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

words following "use" or "using"

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

 HasFactory

-0.57

Personensuche

-0.51

Искәрмәләр

-0.51

domada

-0.50

 createSlice

-0.47

AccessorTable

-0.47

Kanpo

-0.44

iseite

-0.44

endpush

-0.43

\{\\

-0.41

POSITIVE LOGITS

LabelTagHelper

0.51

 تضيفلها

0.45

 NSCoder

0.44

MigrationBuilder

0.41

 CreateTagHelper

0.39

__*/

0.38

getSimpleName

0.37

 felhasznál

0.35

tagHelperRunner

0.35

Activations Density 0.042%

references to keywords and instructions for usage or description

words following "use" or "using"

No Comments

No Known Activations