INDEX

Explanations

verbs related to classification, organization, or categorization processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ⓧ

-0.67

 Vikipedi

-0.59

 Haga

-0.55

razos

-0.55

BuildContext

-0.54

 onAnimation

-0.52

 Catawiki

-0.52

 Schein

-0.52

izaci

-0.52

 Valhalla

-0.52

POSITIVE LOGITS

ed

1.24

ted

0.94

bed

0.90

ED

0.89

oned

0.86

hed

0.85

ned

0.85

ked

0.84

ined

0.84

ved

0.83

Activations Density 0.411%

verbs related to classification, organization, or categorization processes

No Comments

No Known Activations