INDEX

Explanations

references to individuals and their professional roles or affiliations

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

setVerticalGroup

-1.13

 CreateTagHelper

-1.02

MigrationBuilder

-0.81

 AssemblyCulture

-0.81

TargetException

-0.72

AndEndTag

-0.72

+#+#

-0.69

ScopeManager

-0.68

脚注の使い方

-0.66

 Мексичка

-0.65

POSITIVE LOGITS

 past

0.52

</table>

0.45

 Warszaw

0.44

Provision

0.43

 left

0.43

vue

0.43

odils

0.42

<eos>

0.42

View

0.41

venser

0.41

Activations Density 0.212%

references to individuals and their professional roles or affiliations

No Comments

No Known Activations