INDEX

Explanations

statements that clarify important points or emphasize clarity in communication

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

 unexpectedly

-0.53

 perchance

-0.52

magine

-0.52

Akhir

-0.51

 Económica

-0.49

atshirt

-0.49

[]:

-0.48

 yogur

-0.48

ראה

-0.48

җ

-0.47

POSITIVE LOGITS

 فريبيس

0.79

 nahilalakip

0.77

ScopeManager

0.75

principalColumn

0.75

あくまで

0.71

InputTagHelper

0.67

 Exacts

0.66

 '\\;'

0.65

 protoimpl

0.63

Personendaten

0.63

Activations Density 0.087%

statements that clarify important points or emphasize clarity in communication

No Known Activations