INDEX

Explanations

high numeric values indicating importance or emphasis in a technical context

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

Code snippets/programming syntax

np_acts-logits-general · gemini-2.0-flash

game system statuses

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Datuak

-0.82

lotz

-0.80

 ویکی‌پدیای

-0.76

mnt

-0.76

 autorytatywna

-0.75

methe

-0.69

ifoli

-0.67

外部リンク

-0.67

 lenker

-0.67

jonal

-0.66

POSITIVE LOGITS

enumi

0.81

WebVitals

0.73

 متعلقه

0.73

[toxicity=0]

0.72

intios

0.71

0.65

__))

0.65

aryen

0.64

AEC

0.63

رشف

0.63

Activations Density 0.031%

high numeric values indicating importance or emphasis in a technical context

Code snippets/programming syntax

game system statuses

No Comments

No Known Activations