INDEX

Explanations

terms related to data processing and indexing in arrays

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

HSV channel processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

awaiter

-0.44

 liderança

-0.37

บ้าง

-0.36

 sumpay

-0.36

 للمعارف

-0.36

 FishBase

-0.36

=="

-0.34

 bạo

-0.34

 saying

-0.34

settings

-0.34

POSITIVE LOGITS

RuleContext

0.60

CPtr

0.51

InstrumentedTest

0.50

WriteTagHelper

0.49

IBOutlet

0.48

migrationBuilder

0.48

 насељу

0.47

InSection

0.47

webElementXpaths

0.46

 klachten

0.45

Activations Density 0.014%

terms related to data processing and indexing in arrays

HSV channel processing

No Comments

No Known Activations