INDEX

Explanations

symbols and notations used in mathematical or programming contexts

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

code and math syntax

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

وصلات

-0.42

 صوتيه

-0.42

eth

-0.41

Eth

-0.41

addContainerGap

-0.41

Eth

-0.41

BER

-0.40

 GetEnumerator

-0.40

ethene

-0.39

 tắt

-0.39

POSITIVE LOGITS

bewerken

0.60

HomeAsUp

0.45

CppCodeGen

0.44

 MemoryStream

0.44

 Comprometido

0.44

MenuInflater

0.41

 Halsey

0.40

 redacción

0.40

点此举报

0.39

 myſelf

0.39

Activations Density 0.031%

symbols and notations used in mathematical or programming contexts

code and math syntax

No Comments

No Known Activations