INDEX

Explanations

references to legal terminology, particularly in relation to judgments and objections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

kheim

-0.63

culously

-0.57

NSError

-0.57

aarrggbb

-0.55

ázky

-0.55

livia

-0.55

 Cair

-0.55

="<?=

-0.53

setCellValue

-0.53

uertos

-0.51

POSITIVE LOGITS

franchise

0.89

 franchise

0.78

ⓧ

0.78

Franchise

0.74

 franchises

0.73

unmodifiable

0.70

 Franchise

0.70

franch

0.68

 franquicia

0.66

 franchi

0.64

Activations Density 0.860%

references to legal terminology, particularly in relation to judgments and objections

No Comments

No Known Activations