INDEX

Explanations

snippets of code or programming-related content

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

programming code fragments

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

хьтан

-0.46

entistas

-0.41

 SPOILERS

-0.40

foria

-0.40

hyrchwyd

-0.39

endphp

-0.39

RTEE

-0.39

 typelib

-0.38

期刊论文

-0.38

 Tumble

-0.38

POSITIVE LOGITS

mybatisplus

0.54

 referrerpolicy

0.49

ValueStyle

0.46

 <=",

0.44

BASEPATH

0.44

sz

0.43

:✨

0.43

 juge

0.42

 <>",

0.41

\{\\

0.40

Activations Density 0.003%

snippets of code or programming-related content

programming code fragments

No Comments

No Known Activations