INDEX

Explanations

indicators of engagement and interaction in a conversation or content

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

Code or numerical data within text

np_acts-logits-general · gemini-2.0-flash

enter code here with numbers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

APORE

-0.52

äiv

-0.50

chuga

-0.47

jacency

-0.47

UrlResolution

-0.47

Todavía

-0.46

newValue

-0.45

lccn

-0.45

 BoxFit

-0.45

 antaranya

-0.45

POSITIVE LOGITS

 يتيمه

0.68

 متعلقه

0.61

Jegyzetek

0.57

naires

0.56

AddTagHelper

0.56

 المعرف

0.55

السكان

0.55

Демографія

0.54

})();

0.53

évaluateur

0.53

Activations Density 0.051%

indicators of engagement and interaction in a conversation or content

Code or numerical data within text

enter code here with numbers

No Comments

No Known Activations