INDEX

Explanations

numeric values and their contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Autowired

-0.81

ंदीखरीदारी

-0.64

Wiener

-0.61

ochet

-0.61

 newBuilder

-0.61

 Lewis

-0.60

preloader

-0.60

Explicación

-0.59

WV

-0.58

raulic

-0.58

POSITIVE LOGITS

NOPQRST

0.85

ioutil

0.78

awtextra

0.71

 Acme

0.71

 Exactos

0.69

 Tarragona

0.67

CSM

0.67

öffentlichen

0.65

ároz

0.65

 Kości

0.63

Activations Density 0.158%

numeric values and their contexts

No Comments

No Known Activations