INDEX

Explanations

terms related to scientific and medical concepts, particularly focusing on treatment, diagnostics, and legal issues

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

 <<<<<<<<<<<<<<

-0.68

Personensuche

-0.66

__*/

-0.65

ThroughAttribute

-0.65

 occidentale

-0.56

 reconnu

-0.50

 professionale

-0.50

 supérieurs

-0.49

 tecnici

-0.49

 promet

-0.48

POSITIVE LOGITS

yarnpkg

0.70

ConstraintMaker

0.69

 disambiguazione

0.66

Manbalar

0.60

ThemeOverlay

0.60

حياته

0.60

rvore

0.59

 للمعارف

0.59

Geplaatst

0.58

Παραπομπές

0.57

Activations Density 0.532%

terms related to scientific and medical concepts, particularly focusing on treatment, diagnostics, and legal issues

No Comments

No Known Activations