INDEX

Explanations

references to storage and storage-related concepts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

data or material storage

np_acts-logits-general · gemini-2.0-flash

storage tanks, prices, conditions, space, devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 GetEnumerator

-0.57

 telefónica

-0.56

TintMode

-0.55

Collegamenti

-0.53

ParallelGroup

-0.52

 intoxication

-0.52

FunctionFlags

-0.52

hemian

-0.52

 éditoriale

-0.50

︎

-0.50

POSITIVE LOGITS

house

0.66

multer

0.64

houses

0.61

medium

0.53

 compartments

0.53

 capacity

0.52

 Waray

0.52

 cupboard

0.52

MethodManager

0.51

XSS

0.51

Activations Density 0.110%

references to storage and storage-related concepts

data or material storage

storage tanks, prices, conditions, space, devices

No Known Activations