INDEX

Explanations

concepts related to mathematical definitions and properties, particularly those involving prime factors and cohomology in algebraic contexts

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

Preceding words of "representation"

np_acts-logits-general · gemini-2.0-flash

representation and convenient

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

Portály

-0.55

GEBURTSDATUM

-0.55

RegressionTest

-0.54

Autoritní

-0.53

 foreseeable

-0.53

randomUUID

-0.53

ilogue

-0.52

krom

-0.52

 Dile

-0.52

 expect

-0.51

POSITIVE LOGITS

tonode

0.78

 representation

0.75

convenient

0.70

setVerticalGroup

0.65

 удобно

0.63

Convenient

0.62

principalTable

0.61

 convenient

0.61

representation

0.60

 pulmonar

0.58

Activations Density 1.623%

concepts related to mathematical definitions and properties, particularly those involving prime factors and cohomology in algebraic contexts

Preceding words of "representation"

representation and convenient

No Comments

No Known Activations