INDEX

Explanations

references to items being named or labeled

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

Precedes words after "called"

np_acts-logits-general · gemini-2.0-flash

introducing the name or designation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

ValueStyle

-0.58

出版年

-0.55

 Asie

-0.52

 Houſe

-0.51

 Avez

-0.50

 Sopho

-0.50

 Pentecost

-0.49

Yoh

-0.48

 houſe

-0.48

Uff

-0.47

POSITIVE LOGITS

“

1.04

«

0.88

„

0.82

‘

0.81

]=="

0.77

']='

0.73

0.71

"=>"

0.70

「

0.70

Activations Density 0.157%

references to items being named or labeled

Precedes words after "called"

introducing the name or designation

No Comments

No Known Activations