INDEX

Explanations

high numerical scores and measures associated with performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 szóci

-0.79

 ErrIntOverflow

-0.72

 lenker

-0.69

RenderAtEndOf

-0.67

}}^{(

-0.67

UseVisualStyle

-0.66

Personensuche

-0.65

webElementGuid

-0.65

Geplaatst

-0.64

 utafitiHapana

-0.64

POSITIVE LOGITS

LEncoder

0.65

0.52

withIdentifier

0.48

½

0.47

ToAction

0.45

 Isis

0.41

½

0.41

something

0.40

Disaster

0.40

Activations Density 0.775%

high numerical scores and measures associated with performance metrics

No Comments

No Known Activations