INDEX

Explanations

code syntax, particularly focusing on structural elements like braces and method definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

RefNanny

-0.68

 resourceCulture

-0.64

basicConfig

-0.61

treeview

-0.56

KommentareTeilen

-0.55

 StyleSheet

-0.53

Personendaten

-0.52

StoryboardSegue

-0.52

 ostavi

-0.51

 doigt

-0.51

POSITIVE LOGITS

 дописавши

0.52

ranton

0.48

eavour

0.45

宾

0.45

‍♀️

0.44

וא

0.42

 gynhyrchwyd

0.42

 Yale

0.42

BagLayout

0.42

 apologizing

0.41

Activations Density 0.064%

code syntax, particularly focusing on structural elements like braces and method definitions

No Comments

No Known Activations