INDEX

Explanations

abbreviations and acronyms related to specific scientific and technical terms

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

Not in Any Lists

No Comments

Negative Logits

Hauptartikel

-0.54

setVerticalGroup

-0.52

rschein

-0.50

DMETHOD

-0.50

mergeFrom

-0.47

anmar

-0.46

 ragione

-0.45

 gäller

-0.43

ออก

-0.42

ceği

-0.42

POSITIVE LOGITS

matchCondition

0.64

 kapturem

0.60

 totality

0.57

idency

0.55

actéristique

0.55

bitos

0.55

HU

0.54

 Fris

0.54

EndContext

0.54

ateľ

0.54

Activations Density 0.075%

abbreviations and acronyms related to specific scientific and technical terms

No Comments

No Known Activations

abbreviations and acronyms related to specific scientific and technical terms

No Comments

No Known Activations