INDEX

Explanations

programming constructs and actions related to data manipulation or database management

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

removes or deletes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ArgsConstructor

-0.43

 enga

-0.42

enderror

-0.41

ATURE

-0.40

styleType

-0.40

 interpreta

-0.38

 interpretación

-0.38

GTCX

-0.38

GroupLayout

-0.37

 consultato

-0.37

POSITIVE LOGITS

 purge

0.64

SharedDtor

0.62

 remove

0.62

DeleteMapping

0.62

 removal

0.62

 removing

0.59

purge

0.59

 delete

0.57

 removes

0.57

 Remove

0.55

Activations Density 0.037%

programming constructs and actions related to data manipulation or database management

removes or deletes

No Comments

No Known Activations