INDEX

Explanations

specific programming annotations and context definitions in code

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

gonic

-0.67

wäsche

-0.52

drawSprites

-0.51

hared

-0.47

bewah

-0.47

ModelMap

-0.47

 Cambio

-0.47

 basi

-0.46

 boxes

-0.45

stationary

-0.45

POSITIVE LOGITS

HasAnnotation

1.09

SourceChecksum

0.89

("")]

0.83

oredCriteria

0.82

 незавершена

0.79

 makeStyles

0.79

NameInMap

0.79

)";

0.76

ftagPool

0.76

GeneratedValue

0.75

Activations Density 0.028%

specific programming annotations and context definitions in code

No Comments

No Known Activations