INDEX

Explanations

references to target objects or variables in programming contexts

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

target

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 незавершена

-0.55

 createdBy

-0.52

Geplaatst

-0.48

 FormsModule

-0.48

UpInside

-0.47

}?>

-0.47

 fileSize

-0.46

 JSTOR

-0.46

 rowCount

-0.45

endphp

-0.44

POSITIVE LOGITS

target

1.32

Target

1.23

 Target

1.13

TARGET

1.06

 target

1.06

getTarget

1.02

 TARGET

0.98

 getTarget

0.91

arget

0.85

TargetException

0.85

Activations Density 0.013%

references to target objects or variables in programming contexts

target

No Comments

No Known Activations