INDEX

Explanations

terms related to locations or places

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

a location

np_acts-logits-general · gemini-2.0-flash

somewhere, anywhere, nowhere

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

日閲覧

-0.56

dotenv

-0.52

ung

-0.51

-0.49

//

-0.49

峙

-0.48

 many

-0.48

en

-0.48

 GenerationType

-0.48

POSITIVE LOGITS

 else

1.03

下载附件

0.69

 Else

0.66

 Wikispecies

0.66

󠁢

0.64

 Nowhere

0.64

Else

0.63

Jîn

0.60

afo

0.59

 anytime

0.59

Activations Density 0.063%

terms related to locations or places

a location

somewhere, anywhere, nowhere

No Comments

No Known Activations