INDEX

Explanations

references to updates about applications or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 level

-0.32

 extinción

-0.31

 seuls

-0.28

 coming

-0.27

 having

-0.26

 being

-0.26

 continued

-0.26

 cooperación

-0.26

 pousser

-0.25

 board

-0.25

POSITIVE LOGITS

 AssemblyCulture

1.09

parsedMessage

0.84

DockStyle

0.82

niſſe

0.81

 Paglinawan

0.76

IntoConstraints

0.75

ValueStyle

0.75

tagext

0.75

 utafitiHapana

0.74



0.74

Activations Density 0.599%

references to updates about applications or systems

No Comments

No Known Activations