INDEX

Explanations

indicative markers or formatting that suggests parts of a dialogue or narrative flow

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

+#+#

-0.77

 autorytatywna

-0.61

 aDecoder

-0.60

 المعيارى

-0.60

IVEREF

-0.60

 MenuView

-0.58

 onAnimation

-0.58

 varargin

-0.58

ItemBackground

-0.57

($__

-0.55

POSITIVE LOGITS

-->

1.06

-->

0.80

-->

0.78

*/;

0.77

>-->

0.73

ngdoc

0.72

 nahilalakip

0.70

<!--

0.68

*/;

0.67

 JADX

0.66

Activations Density 0.044%

indicative markers or formatting that suggests parts of a dialogue or narrative flow

No Comments

No Known Activations