INDEX

Explanations

interactions and relationships between concepts or entities

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

ésult

-0.49

 étoient

-0.47

 feroit

-0.46

 pouvoit

-0.45

tées

-0.44

 avoient

-0.44

 régime

-0.44

 BoxFit

-0.44

 mourut

-0.42

 faſt

-0.41

POSITIVE LOGITS

InjectAttribute

0.57

下载附件

0.55

UnusedPrivate

0.54

 THEN

0.51

 потім

0.46

 потом

0.45

 later

0.45

THEN

0.45

 затем

0.44

 then

0.44

Activations Density 0.749%

interactions and relationships between concepts or entities

No Comments

No Known Activations