INDEX

Explanations

technical terms and concepts related to electrical engineering and dependencies in systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

$.

-0.43

ش

-0.42

nor

-0.42

↵↵↵↵

-0.41

urum

-0.41

мян

-0.40

ван

-0.39

ixos

-0.39

Nor

-0.39

 congi

-0.39

POSITIVE LOGITS

elemField

0.88

 resourceCulture

0.87

 AssemblyCulture

0.83

ViewFeatures

0.83

 समीक्षाओं

0.80

StoryboardSegue

0.74

RectangleBorder

0.74

 للاسماء

0.73

fjspx

0.73

 мәкал

0.72

Activations Density 0.942%

technical terms and concepts related to electrical engineering and dependencies in systems

No Comments

No Known Activations