INDEX

Explanations

numerical data and statistics related to various topics

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

Numbers between 0 and 9,999

np_acts-logits-general · gemini-2.0-flash

numbers followed by units

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

LookAnd

-0.73

 Reſ

-0.64

Efq

-0.64

 leaſt

-0.64

 lenker

-0.63

 Theſe

-0.63

 cauſe

-0.61

 ✭✭

-0.61

 houſe

-0.60

ArgsConstructor

-0.59

POSITIVE LOGITS

something

0.72

 something

0.63

多

0.59

Something

0.58

(!)

0.56

 Something

0.56

matchCondition

0.55

了几

0.53

 περί

0.53

(!)

0.51

Activations Density 0.369%

numerical data and statistics related to various topics

Numbers between 0 and 9,999

numbers followed by units

No Comments

No Known Activations