INDEX

Explanations

references to code vulnerabilities or security issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 OFDb

-0.57

 crucial

-0.48

---

-0.46

—

-0.45

us

-0.45

ствовал

-0.43

向

-0.43

--

-0.43

-0.42

POSITIVE LOGITS

RectangleBorder

1.10

]")]

1.00

nationality

0.93

</caption>

0.83

InputBorder

0.81

 GoogleFonts

0.79

脚注の使い方

0.78

 InputDecoration

0.78

bibfield

0.74

 مرئيه

0.74

Activations Density 0.006%

references to code vulnerabilities or security issues

No Comments

No Known Activations