INDEX

Explanations

terms and phrases that relate to definitions or the act of defining something

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

"defined" or "definition"

np_acts-logits-general · gemini-2.0-flash

defined as or by

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

 financière

-0.69

Kjelder

-0.66

EndContext

-0.65

keyColumn

-0.59

ladiator

-0.59

IContainer

-0.58

 Betracht

-0.58

sieur

-0.56

ฤษ

-0.55

ioutil

-0.54

POSITIVE LOGITS

tely

1.09

 Paglinawan

0.67

writeFieldEnd

0.66

 Defines

0.65

 BoxFit

0.64

]='\

0.64

 undef

0.62

 Defin

0.60

 LUMP

0.60

ViewFeatures

0.59

Activations Density 0.103%

terms and phrases that relate to definitions or the act of defining something

"defined" or "definition"

defined as or by

No Comments

No Known Activations