INDEX

Explanations

programming language constructs related to variable declarations and memory management

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

code structure and declarations

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

 Wicidata

-0.97

 betweenstory

-0.88

 <<<<<<<<<<<<<<

-0.84

 nakalista

-0.84

 autorytatywna

-0.81

 defaultstate

-0.78

 становника

-0.76

 pinulongan

-0.76

KommentareTeilen

-0.73

ロウィン

-0.72

POSITIVE LOGITS

 medios

0.28

 louer

0.27

 moyens

0.25

HasColumnType

0.25

 cuerdas

0.24

 mensuales

0.23

 tyle

0.23

 moyen

0.23

 embora

0.23

 rangs

0.23

Activations Density 0.066%

programming language constructs related to variable declarations and memory management

code structure and declarations

No Comments

No Known Activations