INDEX

Explanations

terms related to electrical and health-related concepts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

 cherchés

-0.60

GNP

-0.56

 PyLong

-0.55

 RSSSF

-0.52

AutoresizingMask

-0.52

COE

-0.51

дові

-0.51

 iprot

-0.50

vably

-0.50

ódz

-0.50

POSITIVE LOGITS

inigungs

0.64

createCanvas

0.60

PhysRevLett

0.60

 createSlice

0.54

 PhpStorm

0.51

PhysRev

0.51

SourceChecksum

0.51

против

0.50

MessageOf

0.50

èdia

0.50

Activations Density 0.017%

terms related to electrical and health-related concepts

No Known Activations