INDEX

Explanations

reflections on personal realizations and unexpected insights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disjoint

-0.57

 synap

-0.50

downe

-0.49

期刊论文

-0.48

rspec

-0.48

 only

-0.48

deviantart

-0.48

 equity

-0.48

ABASES

-0.47

 ?>">

-0.47

POSITIVE LOGITS

 оригіналу

0.69

原來

0.62

 réal

0.57

 ExecuteAsync

0.56

 dimensión

0.55

WEBPACK

0.52

 AssemblyCulture

0.52

 until

0.51

ForResult

0.50

until

0.49

Activations Density 0.269%

reflections on personal realizations and unexpected insights

No Comments

No Known Activations