INDEX

Explanations

technical and structured information related to uploads and downloads

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

estacks

-0.73

 itſelf

-0.67

Mev

-0.63

 Diſ

-0.62

 ſeveral

-0.60

AnimationsModule

-0.60

 reaſon

-0.59

 purpoſe

-0.59

InputLabel

-0.59

 themſelves

-0.58

POSITIVE LOGITS

 BoxDecoration

0.56

новниш

0.53

Obrázky

0.52

::~

0.51

htë

0.51

__':

0.50

'}';

0.49

 AssemblyTitle

0.47

 tartalomajánló

0.47

Bioaccumulative

0.47

Activations Density 0.863%

technical and structured information related to uploads and downloads

No Comments

No Known Activations