INDEX

Explanations

concepts related to legitimacy and decision-making processes

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

by or from

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

ContentAsync

-0.37

ovatel

-0.36

anggap

-0.35

 Bär

-0.33

 Scratch

-0.33

 TARGET

-0.33

 Públicas

-0.32

辅

-0.32

もし

-0.32

 себе

-0.32

POSITIVE LOGITS

########.

0.64

 estekak

0.60

 autorytatywna

0.56

DockStyle

0.56

Hentet

0.53

 nakalista

0.52

 utafitiHapana

0.52

WithIOException

0.52

 linkovi

0.52

IsMutable

0.51

Activations Density 0.179%

concepts related to legitimacy and decision-making processes

by or from

No Comments

No Known Activations