INDEX

Explanations

code snippets or blocks of code within a document

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

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

 المعيارى

-0.87

aarrggbb

-0.79

transQ

-0.62

 renang

-0.62

يكب

-0.61

/*

-0.60

UpInside

-0.59

 LCCN

-0.58

 ComVisible

-0.58

 DialogInterface

-0.57

POSITIVE LOGITS

```

0.67

 שוליים

0.63

 cref

0.56

ReusableCell

0.55

anum

0.53

entuh

0.53

 sumpay

0.52

```

0.51

حيط

0.50

 Pearls

0.50

Activations Density 0.156%

code snippets or blocks of code within a document

No Comments

No Known Activations