INDEX

Explanations

programming and technical terms related to development and data structures

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

code delimiters and keywords

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

➞

-0.39

WebElementEntity

-0.37

 olsun

-0.32

 ammat

-0.32

 sää

-0.31

vœ

-0.31

 pendek

-0.31

 kanssa

-0.30

 Tatsache

-0.30

drawSprites

-0.30

POSITIVE LOGITS

:✨

0.87

ValueStyle

0.82

webElementXpaths

0.82

MessageOf

0.77

WireFormatLite

0.77

 CreateTagHelper

0.73

WithIOException

0.71

httphttps

0.68

 lenker

0.67

IUrlHelper

0.67

Activations Density 0.166%

programming and technical terms related to development and data structures

code delimiters and keywords

No Comments

No Known Activations