INDEX

Explanations

expressions of disbelief or humor related to ridiculous situations

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

 doInBackground

-0.79

Personensuche

-0.77

LookAnd

-0.74

extAlignment

-0.62

あくまで

-0.62



-0.60

mybatisplus

-0.59

قایناق‌لار

-0.58

 ailleurs

-0.57

一応

-0.57

POSITIVE LOGITS

incredible

0.65

 amazing

0.64

amazing

0.63

多么

0.63

 چقدر

0.63

Amazing

0.62

 Amazing

0.61

Wonderful

0.60

 incredible

0.60

wonderful

0.58

Activations Density 0.234%

expressions of disbelief or humor related to ridiculous situations

No Comments

No Known Activations