INDEX

Explanations

word sequences that suggest probability or reasonableness

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

Code snippets and non-English text

np_acts-logits-general · gemini-2.0-flash

Introduction, Free, Treatments, Fire

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

endphp

-0.77

 فريبيس

-0.76

 שוליים

-0.73

<",

-0.70

WebServlet

-0.70

'])->

-0.68

[…]

-0.66

✭✭

-0.64

 المعيارى

-0.63

>*/

-0.62

POSITIVE LOGITS

 inderdaad

0.86

LookAnd

0.70

 Signalez

0.67

 ครับ

0.64

ครับ

0.58

 parseFrom

0.55

 effectivement

0.55

 kérdés

0.55

 AssemblyCompany

0.54

そうですね

0.54

Activations Density 0.559%

word sequences that suggest probability or reasonableness

Code snippets and non-English text

Introduction, Free, Treatments, Fire

No Comments

No Known Activations