INDEX

Explanations

terms related to distraction and being distracted

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

distraction and diversion

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

providedIn

-0.57

 overeen

-0.56

pexpr

-0.51

 כן

-0.48

Ngb

-0.46

Autoritní

-0.45

 Geben

-0.43

UserScript

-0.43

bestimmungen

-0.41

 Partagez

-0.41

POSITIVE LOGITS

 distraction

1.27

 distractions

1.12

 distract

1.11

 distracted

1.06

 distracting

1.05

 distra

1.02

 Distra

0.93

 diversion

0.76

 Diversion

0.68

 DISTR

0.65

Activations Density 0.005%

terms related to distraction and being distracted

distraction and diversion

No Comments

No Known Activations