INDEX

Explanations

references to notable individuals and their titles or roles

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

quotes and titles

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

ніципалі

-0.57

吋

-0.55

webElementXpaths

-0.54

цездатний

-0.47

 linkovi

-0.47

ⓧ

-0.46

Enllaços

-0.46

 autorytatywna

-0.45

addPreferredGap

-0.45

yfikacja

-0.45

POSITIVE LOGITS

³.

0.47

++.

0.45

.$$

0.44

.\\

0.42

UserScript

0.40

__.

0.40

®.

0.40

².

0.39

Ӕ

0.39

Activations Density 0.015%

references to notable individuals and their titles or roles

quotes and titles

No Comments

No Known Activations