INDEX

Explanations

discussions about uncertainty and opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

出版年

-0.90

ymce

-0.88

MessageTagHelper

-0.84

 AppCompatTheme

-0.83

DockStyle

-0.82

SourceChecksum

-0.74

InputBorder

-0.73

 Wiktionnaire

-0.72

rawDesc

-0.71

apunov

-0.70

POSITIVE LOGITS

panel

0.47

alı

0.41

 discorso

0.40

ona

0.40

order

0.40

wor

0.39

ContextHolder

0.39

 разве

0.38

śmie

0.38

খ

0.38

Activations Density 0.166%

discussions about uncertainty and opinion

No Comments

No Known Activations