INDEX

Explanations

statistical values and comparisons within data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

asteroide

-0.48

yym

-0.46

utz

-0.46

ksikon

-0.46

افية

-0.44

setObjectName

-0.44

theon

-0.43

 caribou

-0.43

 foramen

-0.43

kammer

-0.43

POSITIVE LOGITS

GEBURTSDATUM

1.03

DoubleQuotes

0.85

 الحره

0.77

Geplaatst

0.75

 ExecuteAsync

0.73

RetentionPolicy

0.67

OGND

0.66

رشف

0.66

endpush

0.65

Brainz

0.64

Activations Density 1.027%

statistical values and comparisons within data

No Comments

No Known Activations