INDEX

Explanations

terms related to belonging and classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ViewFeatures

-0.67

tagHelperRunner

-0.63

amp

-0.63

ChromeDriver

-0.62

jupiter

-0.59

 numberWith

-0.58

AxisAlignment

-0.58

agreb

-0.58

AccessFile

-0.58

 MainAxisSize

-0.58

POSITIVE LOGITS

Jop

0.90

 Belong

0.88

 belongs

0.85

belongs

0.83

 belong

0.82

 Correspond

0.81

 belonging

0.81

 Linger

0.77

SerializeField

0.76

melse

0.75

Activations Density 0.171%

terms related to belonging and classification

No Comments

No Known Activations