INDEX

Explanations

different forms and variations of a concept or item

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IsContent

-0.75

BeginContext

-0.73

IntoConstraints

-0.68

ScopeManager

-0.66

DatabaseError

-0.60

ticon

-0.59

tadiene

-0.59

anuts

-0.57

@"/

-0.57

 Italijanski

-0.56

POSITIVE LOGITS

 variant

1.22

 versions

1.20

 variants

1.15

 variantes

1.12

 version

1.07

 variante

1.02

 Variants

1.00

 Versions

0.96

 Varianten

0.94

variant

0.93

Activations Density 0.143%

different forms and variations of a concept or item

No Comments

No Known Activations