INDEX

Explanations

programming-related terms, specifically those that deal with function parameters and arguments

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

parameters and arguments

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

InjectAttribute

-0.66

 ब्रेकडाउन

-0.65

chieht

-0.59

endphp

-0.57

 nakalista

-0.57

Tikang

-0.56

SequentialGroup

-0.56

Portale

-0.54

EndContext

-0.52

ésultats

-0.50

POSITIVE LOGITS

sohn

0.35

eg

0.34

araan

0.34

ißt

0.34

[@"

0.31

CHANGED

0.30

 pertinente

0.30

 variar

0.29

ResponseWriter

0.29

 sympath

0.29

Activations Density 0.059%

programming-related terms, specifically those that deal with function parameters and arguments

parameters and arguments

No Comments

No Known Activations