INDEX

Explanations

references to evidence and organization frameworks

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

<eos>

-0.49

↵↵

-0.43

monių

-0.41

 carico

-0.41

 bulk

-0.39

 sicurezza

-0.39

 alrededores

-0.39

>//

-0.36

????

-0.36

Carreira

-0.35

POSITIVE LOGITS

Cyfeiriadau

1.10

AndEndTag

1.03

GraphicsUnit

0.89

awaiter

0.86

UnknownFieldSet

0.83

">//

0.82

PageFactory

0.81

CrossRef

0.80

قایناق‌لار

0.79

ponses

0.78

Activations Density 0.669%

references to evidence and organization frameworks

No Comments

No Known Activations