INDEX

Explanations

complex mathematical terms and concepts related to transformations and series

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

Followed by "Borel" or "function"

np_acts-logits-general · gemini-2.0-flash

Borel transform series expansions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

RemoveField

-0.51

 SwitchCompat

-0.47

TagHelpers

-0.46

hob

-0.45

 Citadel

-0.44

 Moreau

-0.44

NetworkInfo

-0.44

onAttach

-0.43

hindu

-0.42

 ComVisible

-0.42

POSITIVE LOGITS

 series

0.84

 recurrence

0.83

series

0.80

 Series

0.79

Series

0.76

 Recur

0.72

 SERIES

0.71

Recur

0.69

 expansions

0.69

 expansion

0.67

Activations Density 2.091%

complex mathematical terms and concepts related to transformations and series

Followed by "Borel" or "function"

Borel transform series expansions

No Comments

No Known Activations