INDEX

Explanations

references to averaging data or values in a scientific context

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

лтамалар

-0.57

Tē

-0.57

Royaume

-0.52

 klick

-0.47

 denk

-0.47

vimento

-0.47

Intersect

-0.47

MPN

-0.47

takt

-0.46

POSITIVE LOGITS

extAlignment

0.73

 nant

0.58

ագրություններ

0.58

averaged

0.57

ForType

0.57

ReusableCell

0.57

 averaging

0.55

TestingModule

0.55

ENCER

0.55

readObject

0.55

Activations Density 0.024%

references to averaging data or values in a scientific context

No Comments

No Known Activations