INDEX

Explanations

terms and definitions, particularly those related to terminology used in specific contexts or fields

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

a defined word or "term"

np_acts-logits-general · gemini-2.0-flash

defining the term

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

__':

-0.64

__":

-0.64

ISupport

-0.49

tahui

-0.49

__":

-0.46

 merve

-0.46

__':

-0.45

RTEE

-0.44

ioutil

-0.44

 مرئيه

-0.44

POSITIVE LOGITS

 term

2.30

 terminology

1.95

 terms

1.85

 Term

1.79

term

1.78

Term

1.76

 TERM

1.67

 terme

1.65

 istilah

1.64

terms

1.60

Activations Density 0.547%

terms and definitions, particularly those related to terminology used in specific contexts or fields

a defined word or "term"

defining the term

No Comments

No Known Activations