INDEX

Explanations

numeric values and structural elements within data sets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Identyfik

-0.57

 hObject

-0.53

PerformLayout

-0.52

 bricolaje

-0.52

embolso

-0.52

 mismas

-0.52

 aliento

-0.51

 samfun

-0.51

 sám

-0.51

arangay

-0.51

POSITIVE LOGITS

 BoxFit

0.48

Tes

0.46

Tes

0.46

TES

0.39

PostInfinity

0.38

 telegraph

0.38

tes

0.36

 wire

0.36

 reca

0.36

Ken

0.35

Activations Density 1.208%

numeric values and structural elements within data sets

No Comments

No Known Activations