INDEX

Explanations

terms related to mathematical functions or variables

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

 policiales

-0.83

theless

-0.82

 Nema

-0.79

 degradability

-0.79

 Nebula

-0.75

airro

-0.74

Spoljašnje

-0.73

terday

-0.72

 lepro

-0.71

 kaikk

-0.71

POSITIVE LOGITS

nnn

0.83

__*/

0.81

Cn

0.72

Xn

0.72

 McIntosh

0.71

omenclature

0.71

SuppressLint

0.70

Cn

0.66

</i>

0.66

Activations Density 0.163%

terms related to mathematical functions or variables

No Comments

No Known Activations

terms related to mathematical functions or variables

No Comments

No Known Activations