INDEX

Explanations

phrases indicating plans or structured proposals

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

plans and their inclusions

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

 disambiguazione

-0.79

 يتيمه

-0.65

 JLabel

-0.62

 MainAxisSize

-0.61

httphttps

-0.60

IsMutable

-0.56

 CreateTagHelper

-0.54

EndContext

-0.52

SharedCtor

-0.52

$_(

-0.51

POSITIVE LOGITS

 plan

1.73

plan

1.62

 plans

1.55

Plan

1.52

plans

1.49

Plans

1.48

 Plan

1.44

 Plans

1.44

 PLAN

1.30

 PLANS

1.30

Activations Density 0.041%

phrases indicating plans or structured proposals

plans and their inclusions

No Comments

No Known Activations