INDEX

Explanations

emotional expressions and the perception of feelings

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

Follows "believe" or "notice"

np_acts-logits-general · gemini-2.0-flash

how

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BorderFactory

-0.69

 raiſ

-0.63

ReusableCell

-0.61

scriptcase

-0.56

 doInBackground

-0.54

 neceſſ

-0.54

 neceff

-0.53

 anzub

-0.53

mybatisplus

-0.53

OutputType

-0.52

POSITIVE LOGITS

how

3.79

how

2.76

How

2.41

How

2.40

 cómo

2.15

HOW

2.10

HOW

2.04

 bagaimana

2.02

 hvordan

1.81

 كيف

1.78

Activations Density 0.576%

emotional expressions and the perception of feelings

Follows "believe" or "notice"

how

No Comments

No Known Activations