INDEX

Explanations

terms related to JSON and data serialization formats

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

"json"

np_acts-logits-general · gemini-2.0-flash

json schema or reader

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

ghijklmnop

-0.56

soever

-0.54

initis

-0.53

liminaries

-0.50

 venit

-0.49

 timeStamp

-0.49

///<

-0.49

تق

-0.48

 dilan

-0.48

 Schuld

-0.48

POSITIVE LOGITS

 незавершена

0.80

 BoxDecoration

0.77

 للمعارف

0.76

 doInBackground

0.68

BeginInit

0.68

rpc

0.68

IonicModule

0.65

jackson

0.65

webtoken

0.65

 Вікі

0.64

Activations Density 0.040%

terms related to JSON and data serialization formats

"json"

json schema or reader

No Comments

No Known Activations