INDEX

Explanations

variable declarations and function definitions in code

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

`#define V_` macros with bit shifts

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

 Metzger

-0.33

Ci

-0.32

 eventually

-0.30

II

-0.30

 early

-0.30

gö

-0.29

мимо

-0.29

six

-0.29

 stark

-0.29

POSITIVE LOGITS

 queſta

0.90

 esternos

0.85

SharedDtor

0.76

SequentialGroup

0.76

 kasarigan

0.73

 ivelany

0.73

Autoritní

0.71

੝

0.71

tvguidetime

0.71

 autorytatywna

0.70

Activations Density 0.019%

variable declarations and function definitions in code

`#define V_` macros with bit shifts

No Comments

No Known Activations