INDEX

Explanations

sections of text that contain numerical data or refer to statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 cobr

-0.59

الحياه

-0.56

transQ

-0.56

цездатний

-0.52

 erop

-0.51

 насељу

-0.51

 nowhere

-0.50

 fört

-0.50

interopRequire

-0.49

 كومونز

-0.48

POSITIVE LOGITS

 Condol

0.77

Condolences

0.77

Condol

0.72

 guestbook

0.70

CloseOperation

0.69

 condolence

0.68

 doInBackground

0.64

 propOrder

0.62

 AssemblyVersion

0.61

 condolences

0.61

Activations Density 0.023%

sections of text that contain numerical data or refer to statistical information

No Comments

No Known Activations