INDEX

Explanations

expressions and actions related to looking and gazing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

CodeDom

-0.72

ActiveRecord

-0.59

OuterClass

-0.58

 Segal

-0.56

skap

-0.54

cursion

-0.54

siven

-0.54

});*/

-0.54

gamot

-0.54

)>>

-0.53

POSITIVE LOGITS

 glance

0.80

 gaze

0.76

 gazing

0.75

 glances

0.71

 staring

0.70

 glancing

0.68

 gazed

0.68

IntoConstraints

0.67

 glanced

0.66

 stare

0.66

Activations Density 0.077%

expressions and actions related to looking and gazing

No Comments

No Known Activations