INDEX

Explanations

text related to coding or programming tasks, especially involving modifications or implementations of code

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

出版年

-0.97

cookieParser

-0.76

__":

-0.66

nical

-0.62

homonymie

-0.61

ագրություններ

-0.60

lineno

-0.60

-0.59

CloseOperation

-0.59

rungsseite

-0.58

POSITIVE LOGITS

 purposely

0.66

してみました

0.65

 purposefully

0.57

 hice

0.54

 sauter

0.53

 below

0.53

 sengaja

0.53

 entered

0.52

 erred

0.52

 hoping

0.52

Activations Density 0.195%

text related to coding or programming tasks, especially involving modifications or implementations of code

No Known Activations