INDEX

Explanations

special characters and formatting notations typically used in data representation or markup

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

antMatchers

-0.79

Tazama

-0.74

Erick

-0.73

WithMany

-0.71

HasColumnType

-0.71

menes

-0.71

addHandler

-0.71

 Erick

-0.69

 يتيمه

-0.69

NewUrlParser

-0.68

POSITIVE LOGITS

<h3>

0.94

<h2>

0.91

 Audiodateien

0.80

↵↵

0.79

0.78

<h4>

0.75

<h1>

0.72

<tbody>

0.71

</table>

0.70

<tr>

0.70

Activations Density 0.030%

special characters and formatting notations typically used in data representation or markup

No Comments

No Known Activations