INDEX

Explanations

mentions of academic or legal terminology related to sentencing and trials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

✥

-0.64

ׂ

-0.57

 урна

-0.55

esteld

-0.54

⎩

-0.54

cedures

-0.53

λον

-0.52



-0.52

ㅐ

-0.52

󠁳

-0.51

POSITIVE LOGITS

Brainz

0.63

 level

0.56

 vectorielle

0.54

warrant

0.54

 Constitucional

0.54

 Finlande

0.54

 vectorielles

0.52

 constitucional

0.52

 warrants

0.51

Попис

0.50

Activations Density 0.679%

mentions of academic or legal terminology related to sentencing and trials

No Comments

No Known Activations