INDEX

Explanations

technical terms related to data management and processing

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

function calls

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

 autorytatywna

-0.73

 Chwiliwch

-0.69

Personendaten

-0.66

 ModelExpression

-0.64

yarnpkg

-0.62

RenderAtEndOf

-0.61

complexContent

-0.61

 snippetHide

-0.60

最快更新

-0.60

tonsoft

-0.57

POSITIVE LOGITS

 обу

0.35

mentioned

0.34

ple

0.33

How

0.32

Tal

0.31

otu

0.30

ورم

0.29

愷

0.29

 обо

0.29

not

0.29

Activations Density 0.082%

technical terms related to data management and processing

function calls

No Comments

No Known Activations