INDEX

Explanations

phrases that denote alternative names or titles of entities

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

 itſelf

-0.73

 Reſ

-0.72

 Majefty

-0.68

 Diſ

-0.66

ſelf

-0.65

 Perſ

-0.64

 geldig

-0.61

 perſon

-0.61

kenny

-0.61

 ſeveral

-0.61

POSITIVE LOGITS

ंदीखरीदारी

0.77

rrggbb

0.69

 CreateTagHelper

0.69

 оригіналу

0.68

ChildScrollView

0.62

enterOuterAlt

0.60

GEBURTSDATUM

0.53

 alia

0.52

culate

0.52

 hoặc

0.52

Activations Density 0.021%

phrases that denote alternative names or titles of entities

No Comments

No Known Activations

phrases that denote alternative names or titles of entities

No Comments

No Known Activations