INDEX

Explanations

mathematical notation and symbols associated with equations or functions within the text

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

Punctuation and symbols within text

np_acts-logits-general · gemini-2.0-flash

percentage or score in parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 quí

-0.47

ViewFeatures

-0.45

umpad

-0.44

 relais

-0.43

multicolumn

-0.43

increments

-0.43

RotationOrder

-0.43

lète

-0.42

 PyLong

-0.42

Cass

-0.42

POSITIVE LOGITS

enderror

0.74

aarrggbb

0.65

EDEFAULT

0.65

BindingResult

0.63

 peggio

0.63

strix

0.62

StructEnd

0.61

 ejus

0.61

Personensuche

0.59

 quæ

0.59

Activations Density 0.718%

mathematical notation and symbols associated with equations or functions within the text

Punctuation and symbols within text

percentage or score in parentheses

No Comments

No Known Activations