INDEX

Explanations

phrases that include articles like "a" and "an" indicating specificity in 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

 Roskov

-0.84

rungsseite

-0.82

StoryboardSegue

-0.82

 createState

-0.79

Personendaten

-0.78

expandindo

-0.75

منابع

-0.72

sidemargin

-0.71

Portail

-0.71

Réalisation

-0.71

POSITIVE LOGITS

 souvent

0.55

OleDb

0.54

 often

0.52

 recent

0.50

recent

0.49

often

0.49

IEEE

0.48

 video

0.47

schlag

0.46

 letter

0.45

Activations Density 0.064%

phrases that include articles like "a" and "an" indicating specificity in context

No Comments

No Known Activations