INDEX

Explanations

references to medical conditions or treatments in a legal or procedural context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵↵

-1.02

'])){

-0.89

']))

-0.82

oredCriteria

-0.81

UserScript

-0.80

NameInMap

-0.78

WebVitals

-0.73

hdashline

-0.73

endpush

-0.71

">//

-0.71

POSITIVE LOGITS

kepada

0.54

 faveur

0.54

 pourrais

0.53

wieś

0.52

 connais

0.52

 seules

0.51

 culturelles

0.50

 tillbaka

0.50

 puol

0.50

 posesión

0.49

Activations Density 0.330%

references to medical conditions or treatments in a legal or procedural context

No Comments

No Known Activations