INDEX

Explanations

references to coding elements and relationships between code components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 mergeFrom

-0.71

ImageContext

-0.67

 htons

-0.61

ThroughAttribute

-0.55

omeness

-0.55

 فريبيس

-0.55

ModelSerializer

-0.54

VIAF

-0.54

acea

-0.53

OGND

-0.53

POSITIVE LOGITS

RELATED

1.26

Related

1.14

Bronnen

0.99

 שוליים

0.95

 RELATED

0.94

 Related

0.92

 ALSO

0.91

READ

0.91

ALSO

0.91

Hochspringen

0.90

Activations Density 0.112%

references to coding elements and relationships between code components

No Comments

No Known Activations