INDEX

Explanations

variables and mathematical symbols in a technical or scientific context

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

Code snippets or mathematical formulas

np_acts-logits-general · gemini-2.0-flash

names or mathematical variables

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 atteinte

-0.47

 umane

-0.47

 تعدى

-0.46

 purpoſe

-0.44

 busiest

-0.43

medad

-0.42

izoen

-0.41

ovali

-0.41

 pleaſure

-0.40

Клуб

-0.39

POSITIVE LOGITS

 Joseph

0.94

 William

0.90

 utafitiHapana

0.90

Joseph

0.83

William

0.82

 Thomas

0.81

 James

0.80

 WILLIAM

0.80

 Charles

0.78

 JOSEPH

0.75

Activations Density 0.604%

variables and mathematical symbols in a technical or scientific context

Code snippets or mathematical formulas

names or mathematical variables

No Comments

No Known Activations