INDEX

Explanations

references to individuals and their roles or identities in a community context

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

one of [group]

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

 arşivlendi

-0.47

℗

-0.45

 propOrder

-0.43

 noDo

-0.42

 gauge

-0.42

Apri

-0.42

 halte

-0.42

 singular

-0.41

ger

-0.40

 Winaray

-0.40

POSITIVE LOGITS

########.

0.42

 allAfrica

0.41

IBOutlet

0.41

 Czę

0.41

 complaining

0.40

 aikaa

0.40

 ActionListener

0.39

Vidite

0.39

 dAtA

0.39

 glück

0.39

Activations Density 0.017%

references to individuals and their roles or identities in a community context

one of [group]

No Comments

No Known Activations