INDEX

Explanations

concepts related to methods and technologies in research or analysis

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

Followed by uppercase letters

np_acts-logits-general · gemini-2.0-flash

legal and technical terminology

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

 Мексичка

-1.03

UserScript

-1.02

GEBURTSDATUM

-1.02

expandindo

-1.01

Obrázky

-0.98

RTLR

-0.95

 onOptions

-0.95

 disambiguazione

-0.94

 nakalista

-0.94

Efq

-0.94

POSITIVE LOGITS

0.69

Sch

0.67

<bos>

0.66

0.65

De

0.65

0.64

0.63

Ch

0.63

Activations Density 1.545%

concepts related to methods and technologies in research or analysis

Followed by uppercase letters

legal and technical terminology

No Comments

No Known Activations