INDEX

Explanations

phrases or instances related to querying or processing questions

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

Ծանոթ

-1.01

ientôt

-0.90

Παραπομπές

-0.87

-------

-0.82

তথ্যসূত্র

-0.76

theless

-0.76

ukunft

-0.75

 NavController

-0.74

lysses

-0.74

ubehör

-0.72

POSITIVE LOGITS

 QString

0.66

QString

0.57

on

0.49

hio

0.49

ベル

0.49

0.48

م

0.48

as

0.48

فحة

0.48

Activations Density 0.003%

phrases or instances related to querying or processing questions

No Known Activations