INDEX

Explanations

references to persistent regional terms or identifiers, specifically relating to the "PR" designation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

CWE

-0.92

 InputDecoration

-0.84

AddTagHelper

-0.82

 feroit

-0.78

Ծանոթ

-0.78

 bénévoles

-0.78

principalColumn

-0.75

 extérieures

-0.74

 blessés

-0.73

 TestBed

-0.72

POSITIVE LOGITS

PR

0.69

Ve

0.62

0.57

0.56

\]

0.55

Tembelea

0.54

Ve

0.53

<em>

0.53

PR

0.53

zky

0.52

Activations Density 0.409%

references to persistent regional terms or identifiers, specifically relating to the "PR" designation

No Comments

No Known Activations