INDEX

Explanations

html comments in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 nakalista

-0.85

formik

-0.78

AndEndTag

-0.76

LookAnd

-0.72

ertale

-0.72

UnknownFields

-0.71

databind

-0.70

SharedDtor

-0.70

Források

-0.68

ChromeDriver

-0.67

POSITIVE LOGITS

<!--

1.74

 <!--

1.26

><!--

1.23

"><!--

1.05

<!--[

0.87

<!--<

0.83

 Jefus

0.79

 themſelves

0.78

 مشارکت‌کنندگان

0.77

<!

0.76

Activations Density 0.075%

html comments in the text

No Comments

No Known Activations