INDEX

Explanations

phrases related to providing further information or definitions

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

 nahilalakip

-0.81

 onOptions

-0.76

RectangleBorder

-0.73

 typelib

-0.71

 Audiodateien

-0.69

 detail

-0.69

MLLoader

-0.66

Bronnen

-0.65

protoimpl

-0.64

 дописавши

-0.62

POSITIVE LOGITS

 passively

0.53

 passive

0.50

Personendaten

0.50

perk

0.49

0.48

Clasificación

0.48

 maar

0.47

 való

0.45

 färg

0.45

 Swartz

0.44

Activations Density 0.025%

phrases related to providing further information or definitions

No Comments

No Known Activations