INDEX

Explanations

elements related to programming or coding structures, especially focusing on defining and including libraries or components in code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InSection

-0.74

LookAnd

-0.71

 AssemblyCompany

-0.71

 onData

-0.67

NameInMap

-0.66

AnimationsModule

-0.66

JsonFormat

-0.62

NamedQuery

-0.62

ContentAsync

-0.60

+#+

-0.60

POSITIVE LOGITS

 Diony

0.74

béco

0.73

agascar

0.68

 Majefty

0.64

 reaſon

0.64

 Piran

0.61

 Shakspeare

0.59

úgó

0.59

limb

0.59

 espagne

0.59

Activations Density 1.094%

elements related to programming or coding structures, especially focusing on defining and including libraries or components in code

No Comments

No Known Activations