INDEX

Explanations

the occurrence of the word "strict" and related variations indicating rigidity or high standards

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

strict/strictly usage

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

MEA

-0.59

Edison

-0.56

 Popcorn

-0.56

 userID

-0.55

 currentValue

-0.55

COA

-0.54

NEM

-0.54

 Selfie

-0.53

 getItemId

-0.53

Enlaces

-0.52

POSITIVE LOGITS

 strict

1.07

strict

0.96

 strictly

0.96

 Strict

0.93

Strict

0.88

Strictly

0.81

 estric

0.80

 Strictly

0.79

 estrictamente

0.72

 ketat

0.72

Activations Density 0.008%

the occurrence of the word "strict" and related variations indicating rigidity or high standards

strict/strictly usage

No Comments

No Known Activations