INDEX

Explanations

mathematical terminology and notation related to functions and dimensions

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

variable w in math contexts

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

styleType

-0.61

 صوتيه

-0.55

醐

-0.53

 disambiguazione

-0.52

APORE

-0.52

principalColumn

-0.50

sohn

-0.50

erty

-0.50

 jScrollPane

-0.50

сылкі

-0.50

POSITIVE LOGITS

0.93

0.88

0.80

WSTR

0.75

0.71

WB

0.64

weakSelf

0.62

 Wednesdays

0.61

 étoient

0.61

WV

0.60

Activations Density 0.327%

mathematical terminology and notation related to functions and dimensions

variable w in math contexts

No Comments

No Known Activations