INDEX

Explanations

terms related to software configurations and settings

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

 curé

-0.49

genossen

-0.47

-0.45

 prêtre

-0.43

cur

-0.42

 alps

-0.42

ol

-0.42

!=

-0.42

gh

-0.42

__

-0.41

POSITIVE LOGITS

ंदीखरीदारी

1.17

 Мексичка

0.99

Personendaten

0.97

)");

0.97

titleMargin

0.94

bonucleic

0.91

 ComVisible

0.90

VersionUID

0.90

 onAnimation

0.90

ImageContext

0.89

Activations Density 0.588%

terms related to software configurations and settings

No Comments

No Known Activations