INDEX

Explanations

terms related to "coroner" and associated medical investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AsUp

-0.73

yntaxException

-0.70

########.

-0.69

 SDLK

-0.65

 FontWeight

-0.59

 bäst

-0.56

">−

-0.55

deniz

-0.55

]:

-0.54

uldade

-0.54

POSITIVE LOGITS

COR

0.72

kor

0.69

 Cornelia

0.68

Kor

0.67

 Cornel

0.64

KOR

0.62

ColumnHeaders

0.59

ReusableCell

0.59

 Corcoran

0.59

ztály

0.58

Activations Density 0.211%

terms related to "coroner" and associated medical investigations

No Comments

No Known Activations