INDEX

Explanations

programming terms related to objects and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

ölker

-0.63

sterious

-0.52

')):

-0.51

DataAnnotations

-0.49

完善

-0.46

ndash

-0.46

ductors

-0.45

URLConnection

-0.45

imaan

-0.45

 kích

-0.44

POSITIVE LOGITS

 name

0.82

 names

0.79

name

0.79

lename

0.72

 productName

0.71

 getName

0.71

 namn

0.69

names

0.67

 Names

0.66

名稱

0.66

Activations Density 0.315%

programming terms related to objects and their properties

No Comments

No Known Activations