INDEX

Explanations

elements related to programming or code definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.41.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

pat

-0.77

gro

-0.77

mus

-0.77

pet

-0.77

tre

-0.76

pen

-0.76

pol

-0.76

hum

-0.76

fan

-0.76

tro

-0.76

POSITIVE LOGITS

 transportation

0.30

 digital

0.28

 transfer

0.28

 installation

0.28

 transmission

0.28

 storage

0.28

 delivery

0.28

 automatic

0.28

 selected

0.28

 additional

0.28

Activations Density 15.800%

elements related to programming or code definitions

No Comments

No Known Activations