INDEX

Explanations

mathematical terms and variables related to functions and computations

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

x,y,uv variables

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

Resistance

-0.37

Admin

-0.37

wildcard

-0.36

 admin

-0.36

 nouveautés

-0.36

 maska

-0.36

 schoon

-0.35

<tfoot>

-0.35

asteroid

-0.35

admin

-0.34

POSITIVE LOGITS

内外

0.56

ReadWrite

0.56

男女

0.54

ImageContext

0.53

NUMX

0.52

rrggbb

0.52

前後

0.51

上下

0.51

前后

0.50

 上下

0.50

Activations Density 0.532%

mathematical terms and variables related to functions and computations

x,y,uv variables

No Comments

No Known Activations