INDEX

Explanations

terms related to statistical significance and analysis, particularly in scientific studies

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

aring

-0.50

inel

-0.48

ewon

-0.48

STIC

-0.46

bes

-0.46

 familiar

-0.44

clar

-0.44

})).

-0.44

astra

-0.44

瞰

-0.43

POSITIVE LOGITS

AsUp

0.80

Tikang

0.79

 noDo

0.74

ParallelGroup

0.72

PMailer

0.69

jspx

0.69

astify

0.69

enderror

0.69

fjspx

0.68

BagConstraints

0.68

Activations Density 1.597%

terms related to statistical significance and analysis, particularly in scientific studies

No Comments

No Known Activations