INDEX

Explanations

segments of code or structured text that indicate documentation or commentary

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

 ExecuteAsync

-0.90

LookAnd

-0.89

 mukana

-0.81

WithIOException

-0.78

alipay

-0.76

 Himo

-0.75

OGS

-0.74

 autorytatywna

-0.73

 MonoBehaviour

-0.73

Sef

-0.73

POSITIVE LOGITS

****************

2.02

*************

1.00

**************

0.99

************

0.97

***************

0.97

***********

0.90

********

0.89

*********/

0.81

*********

0.81

 Audiodateien

0.78

Activations Density 0.003%

segments of code or structured text that indicate documentation or commentary

No Comments

No Known Activations