INDEX

Explanations

sequences of numerical data or references in the text

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

variable and table formatting

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

-------

-0.53

 المعيارى

-0.51

 ModelExpression

-0.47

最快更新

-0.45

PhysRev

-0.44

 sonore

-0.43

 spacers

-0.42

initComponents

-0.42

Autoritní

-0.42

JspWriter

-0.41

POSITIVE LOGITS

/**

0.43

landschaft

0.42

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.42

 Maximilian

0.41

eston

0.40

GW

0.40

tyard

0.39

RowIndex

0.39

SOM

0.39

loren

0.39

Activations Density 0.120%

sequences of numerical data or references in the text

variable and table formatting

No Comments

No Known Activations