INDEX

Explanations

terms related to scientific evaluation and statistical analysis

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ագրություններ

-0.59

 հղումներ

-0.56

KommentareTeilen

-0.55

LabelTagHelper

-0.50

 lari

-0.49

 fallu

-0.48

AddTagHelper

-0.47

jspb

-0.46

:✨

-0.46

 proprement

-0.45

POSITIVE LOGITS

GEBURTSDATUM

0.78

AndEndTag

0.70

 approximation

0.69

 approximate

0.69

 approximations

0.66

Approximate

0.65

 estimates

0.65

 estimate

0.64

InputBorder

0.64

 rough

0.63

Activations Density 0.490%

terms related to scientific evaluation and statistical analysis

No Comments

No Known Activations