INDEX

Explanations

commands and outputs in scripts or code snippets

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

programming code and commands

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

 للمعارف

-0.53

 Normdatei

-0.52

Rhestr

-0.50

 صوتيه

-0.49

 AspNetCore

-0.46

 plomo

-0.45

AutoField

-0.43

 desmotivaciones

-0.42

乓

-0.41

 graduación

-0.40

POSITIVE LOGITS

LookAnd

0.57

errHandler

0.50

 InputDecoration

0.49

AnchorStyles

0.48

DockStyle

0.47

AnimationsModule

0.45

WaitGroup

0.43

 ModelExpression

0.40

ApiModelProperty

0.40

tillas

0.40

Activations Density 0.003%

commands and outputs in scripts or code snippets

programming code and commands

No Comments

No Known Activations