INDEX

Explanations

attributes related to objects or entities in a structured format

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

figures and citations

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lawsuit

-0.38

ListTile

-0.34

 enfans

-0.34

 lower

-0.33

Desc

-0.33

下

-0.33

FlatList

-0.32

Fin

-0.31

 dieux

-0.31

 Belf

-0.31

POSITIVE LOGITS

ScopeManager

0.92

httphttps

0.86

 snippetHide

0.78

GOTREF

0.73

CppMethod

0.72

AndEndTag

0.70

setViewportView

0.66

 ویکی‌پدی

0.66

+#+#

0.65

 للاسماء

0.65

Activations Density 0.001%

attributes related to objects or entities in a structured format

figures and citations

No Comments

No Known Activations