INDEX

Explanations

language related to scientific studies, specifically the words "study", "participants", "recruited", and the setup of the study.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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

 dagegen

-0.57

věd

-0.53

ativement

-0.52

@+

-0.52

 hinting

-0.51

 zelfs

-0.49

 estren

-0.49

 kaarangay

-0.49

 comemor

-0.49

yyr

-0.48

POSITIVE LOGITS

 sample

1.10

 participant

1.09

 sampling

1.05

 participants

1.01

sample

0.98

 Sampling

0.98

 study

0.96

 participante

0.96

 Participants

0.95

Participant

0.95

Activations Density 3.431%

language related to scientific studies, specifically the words "study", "participants", "recruited", and the setup of the study.

No Comments

No Known Activations