INDEX

Explanations

names of actors and references to Common Weakness Enumeration (CWE) codes in programming contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

academic paper citations

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

Negative Logits

 propOrder

-0.72

цездатний

-0.71

Personendaten

-0.68

findpost

-0.65

SequentialGroup

-0.63

parsedMessage

-0.56

 kasarigan

-0.51

ніципалі

-0.50

SharedCtor

-0.50

 Numerade

-0.50

POSITIVE LOGITS

Литература

0.63

 Hemsworth

0.61

unfinished

0.60

resizingMask

0.59

aughey

0.56

ersk

0.55

 mắn

0.54

vssd

0.52

picable

0.52

 insuffisamment

0.52

Activations Density 0.009%

names of actors and references to Common Weakness Enumeration (CWE) codes in programming contexts

academic paper citations

No Known Activations