INDEX

Explanations

terms related to data management and analysis procedures

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

set mathematics notation

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 typelib

-0.70

Autoritní

-0.69

➟

-0.64

 Roskov

-0.63

 nonUne

-0.62



-0.61

 informée

-0.58

InjectAttribute

-0.58

scriptcase

-0.57

󠁴

-0.57

POSITIVE LOGITS

åde

0.30

 together

0.28

 robusta

0.28

 Monro

0.28

越多

0.27

 including

0.27

bez

0.27

发生的

0.27

 aussi

0.26

 certainly

0.26

Activations Density 0.049%

terms related to data management and analysis procedures

set mathematics notation

No Comments

No Known Activations