INDEX

Explanations

specific terms related to health metrics and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

حوالہ

-0.78

WindowConstants

-0.78

awtextra

-0.74

LookAnd

-0.73

 يتيمه

-0.72

AddHtmlAttribute

-0.71

IntoConstraints

-0.71

 AssemblyCulture

-0.69

homonymie

-0.67

Filmographie

-0.66

POSITIVE LOGITS

cluye

0.48

故

0.46

EndContext

0.44

 publiques

0.43

ymce

0.42

atual

0.41

 hơi

0.40

UPAC

0.40

iento

0.40

ulario

0.39

Activations Density 0.398%

specific terms related to health metrics and analysis

No Comments

No Known Activations