INDEX

Explanations

specific technical terms and symbols related to programming and mathematics

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

mathematical and programming contexts

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

“

-0.52

tri

-0.45

«

-0.43

-0.41

Tri

-0.40

 Blue

-0.39

Mal

-0.38

Ser

-0.37

Gre

-0.37

urtstag

-0.37

POSITIVE LOGITS

+#+#

0.72

 faſt

0.70

 desmotivaciones

0.65

 pleaſure

0.64

RenderAtEndOf

0.62

########.

0.61

transQ

0.60

enterOuterAlt

0.60

 ſtate

0.59

 Chriftian

0.59

Activations Density 0.075%

specific technical terms and symbols related to programming and mathematics

mathematical and programming contexts

No Comments

No Known Activations