INDEX

Explanations

references to the term "har" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

abestanden

-0.54

 nakalista

-0.53

fjspx

-0.53

Cindy

-0.52

EDEFAULT

-0.51

 Cindy

-0.51

 Lenz

-0.50

"]}

-0.49

stateProvider

-0.49

 ویکی‌پدیا

-0.48

POSITIVE LOGITS

HAR

1.08

Har

0.95

HAR

0.94

har

0.94

Har

0.91

har

0.89

 Harrell

0.78

 Harwood

0.77

 NDEBUG

0.70

 Harlow

0.70

Activations Density 0.104%

references to the term "har" and its variations

No Comments

No Known Activations