INDEX

Explanations

expressions related to decision-making and consequences

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

actions and consequences

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

and

-0.31

 joined

-0.28

 organiz

-0.27

 gost

-0.26

readline

-0.26

 Zusch

-0.26

PROGRAM

-0.26

 section

-0.26

Joined

-0.26

 updates

-0.25

POSITIVE LOGITS

 autorytatywna

0.94

 nahilalakip

0.78

хьтан

0.75

transQ

0.72

AndEndTag

0.71

ChildScrollView

0.67

tagHelperRunner

0.66

Autoritní

0.65

httphttps

0.64

ItemBackground

0.63

Activations Density 0.186%

expressions related to decision-making and consequences

actions and consequences

No Comments

No Known Activations