INDEX

Explanations

numeric values or codes related to specific categories such as products, statistics, or metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

ßig

-0.49

 дописавши

-0.43

InjectAttribute

-0.42

ppure

-0.41

auteuil

-0.41

lecular

-0.41

HasAnnotation

-0.40

 وتسجيلات

-0.39

lapsingToolbar

-0.38

CopyWith

-0.38

POSITIVE LOGITS

nd

1.38

nds

0.86

ndy

0.74

nd

0.74

ND

0.73

ndry

0.61

Nd

0.59

ndia

0.59

ndt

0.57

ndes

0.57

Activations Density 1.758%

numeric values or codes related to specific categories such as products, statistics, or metrics

No Comments

No Known Activations