INDEX

Explanations

specific keywords related to technological terms and processes

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

Code, symbols, and uncommon terms

np_acts-logits-general · gemini-2.0-flash

special characters or numbers

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

 ویکی‌پدی

-0.72

WriteAttribute

-0.67

सन्दर्भ

-0.64

 kaynağından

-0.61

Espèce

-0.60

AnchorStyles

-0.59

choenen

-0.57

UnsafeEnabled

-0.57

 Мексичка

-0.56

RectangleBorder

-0.55

POSITIVE LOGITS

BindView

0.51

Jegyzetek

0.47

RetentionPolicy

0.47

yntaxException

0.45

הערות

0.44

oa̍t

0.44

awaiter

0.44

endmodule

0.44

MenuInflater

0.43

KommentareTeilen

0.43

Activations Density 0.743%

specific keywords related to technological terms and processes

Code, symbols, and uncommon terms

special characters or numbers

No Comments

No Known Activations