INDEX

Explanations

mathematical terminology related to optimization problems and statistical estimation methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 particular

-0.53

us

-0.50

jardins

-0.49

mu

-0.45

rieux

-0.44

cas

-0.44

-0.42

новништво

-0.42

data

-0.41

POSITIVE LOGITS



0.93

 Anſ

0.88

AsUp

0.88

MigrationBuilder

0.87

 leaſt

0.85

principalColumn

0.84

 ainfi

0.83

 greateſt

0.81

makeConstraints

0.81

bewerken

0.81

Activations Density 0.643%

mathematical terminology related to optimization problems and statistical estimation methods

No Comments

No Known Activations