INDEX

Explanations

phrases related to comparative analysis or evaluation between groups or categories

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

preceding "individual" or "a"

np_acts-logits-general · gemini-2.0-flash

individual or singular concepts

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

AddTagHelper

-0.76

 Italijanski

-0.75

atriz

-0.69

wapV

-0.59

 ModelExpression

-0.56

 >=",

-0.56

Abitanti

-0.53

*/),

-0.53

otesi

-0.52

optera

-0.52

POSITIVE LOGITS

 individual

3.33

individual

3.05

Individual

3.00

 Individual

2.87

 individually

2.79

 INDIVIDUAL

2.57

individ

2.38

 Individ

2.36

 individuales

2.33

Individ

2.28

Activations Density 1.084%

phrases related to comparative analysis or evaluation between groups or categories

preceding "individual" or "a"

individual or singular concepts

No Comments

No Known Activations