INDEX

Explanations

scientific terminology related to measurement and parameters in research contexts

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

TagHelper

-0.61

parseColor

-0.60

DebuggerStep

-0.60

findpost

-0.58

čních

-0.57

SuppressLint

-0.56

ngdoc

-0.56

########.

-0.54

$_['

-0.53

DotNetBar

-0.52

POSITIVE LOGITS

hedrals

0.65

Попис

0.61

apunov

0.60

berra

0.59

ilets

0.59

Memes

0.58

jutant

0.58

PROBLE

0.57

rogels

0.57

igneurs

0.57

Activations Density 1.854%

scientific terminology related to measurement and parameters in research contexts

No Comments

No Known Activations