INDEX

Explanations

structured data entries and their associated properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 named

-0.78

Named

-0.70

 Named

-0.66

 nommé

-0.57

named

-0.57

Name

-0.56

 called

-0.53

Titled

-0.52

 naming

-0.52

名为

-0.51

POSITIVE LOGITS

WriteAttribute

0.80

 description

0.71

adaptiveStyles

0.69

description

0.67

 المعيارى

0.66

getDescription

0.65

 unknownFields

0.65

 referenties

0.64

setDescription

0.61

 Taktlose

0.61

Activations Density 0.253%

structured data entries and their associated properties

No Comments

No Known Activations