INDEX

Explanations

references to components in programming or technical contexts

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

adaptiveStyles

-0.61

 насељу

-0.60

richTextPanel

-0.54

+#+#

-0.54

fillType

-0.52

parsedMessage

-0.49

RegistryLite

-0.49

EndInit

-0.49

EDEFAULT

-0.49

 Chwiliwch

-0.47

POSITIVE LOGITS

 capucha

0.39

flashdata

0.39

basicConfig

0.37

 Aufstieg

0.35

 autón

0.34

ละ

0.34

Ibn

0.33

 typelib

0.33

 cláus

0.32

 razão

0.32

Activations Density 0.854%

references to components in programming or technical contexts

No Comments

No Known Activations