INDEX

Explanations

references to specific applications or proposals in a research context

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

research activities

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

 übrigens

-0.66

 persino

-0.52

Хьажоргаш

-0.52

ailleurs

-0.51

 zelfs

-0.50

MMO

-0.49

 frattempo

-0.48

şört

-0.47

 sowieso

-0.47

Кстати

-0.47

POSITIVE LOGITS

 purpose

0.52

整體

0.39

目的是

0.39

 intent

0.38

 Vereinigte

0.37

Overall

0.37

 целью

0.37

UnusedPrivate

0.36

 Overall

0.36

単

0.36

Activations Density 0.050%

references to specific applications or proposals in a research context

research activities

No Comments

No Known Activations