INDEX

Explanations

references to significant concepts, transformations, and conflicts within societal structures and personal experiences

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

abstract concepts and states

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

OGND

-0.66

 TextAppearance

-0.40

 transfieras

-0.39

TagMode

-0.38

queryInterface

-0.38

Demografia

-0.38

 Platon

-0.36

 Administrativna

-0.35

èces

-0.34

rahman

-0.34

POSITIVE LOGITS

saraba

0.59

AISSEE

0.57

 ujednoznacz

0.52

Kjelder

0.50

AppMethodBeat

0.48

 MainAxisSize

0.46

”:

0.43

cupertino

0.43

 MyBatis

0.41

#+#

0.41

Activations Density 0.058%

references to significant concepts, transformations, and conflicts within societal structures and personal experiences

abstract concepts and states

No Comments

No Known Activations