INDEX

Explanations

references to the term "Central" or related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 just

-0.65

曖昧さ回避

-0.64

 juste

-0.64

far

-0.61

 numberWith

-0.59

Personendaten

-0.59

encodeWith

-0.56

ViewImports

-0.56

Código

-0.55

vaadin

-0.55

POSITIVE LOGITS

ized

0.68

 nervous

0.67

 Nervous

0.65

ize

0.61

IZED

0.60

Nervous

0.60

nervous

0.59

.*")]

0.56

isation

0.56

izing

0.52

Activations Density 0.208%

references to the term "Central" or related concepts

No Comments

No Known Activations