INDEX

Explanations

terms and phrases related to statistical modeling and algorithms

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

assign

-0.42

SceneManagement

-0.42

ubi

-0.41

Brainz

-0.41

蕩

-0.40

atars

-0.40

cloudf

-0.40

klo

-0.40

 pié

-0.39

 élevés

-0.39

POSITIVE LOGITS

 automata

0.75

]--;

0.75

 كومونز

0.70

AutoScale

0.69

 createState

0.68

 automaton

0.67

 صوتيه

0.67

SharedDtor

0.66

 Turing

0.66

 CreateTagHelper

0.65

Activations Density 1.150%

terms and phrases related to statistical modeling and algorithms

No Comments

No Known Activations