INDEX

Explanations

code comments and documentation sections within programming-related text

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

any cytotoxicity up to

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

transQ

-0.79

setVerticalGroup

-0.75

AddTagHelper

-0.74

XmlAccessorType

-0.74

windowFixed

-0.70

 propOrder

-0.70

MigrationBuilder

-0.69

tvguidetime

-0.68

parsedMessage

-0.68

 '\\;'

-0.66

POSITIVE LOGITS

///

0.60

the

0.50

//

0.47

0.40

0.39

0.37

位

0.36

닌

0.36

MW

0.36

It

0.36

Activations Density 0.001%

code comments and documentation sections within programming-related text

any cytotoxicity up to

No Comments

No Known Activations