INDEX

Explanations

references to various items or examples in a list format

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

 CreateTagHelper

-0.56

 IndexPath

-0.56

 يتيمه

-0.55

TestingModule

-0.50

躇

-0.50

 ostavi

-0.49

erdings

-0.48

AxisAlignment

-0.47

 թվական

-0.47

 isComment

-0.47

POSITIVE LOGITS

等等

0.53

などなど

0.52

 others

0.50

etc

0.50

etc

0.47

Atentamente

0.44

 lainnya

0.42

 ועוד

0.42

 many

0.41

 more

0.40

Activations Density 0.274%

references to various items or examples in a list format

No Comments

No Known Activations