INDEX

Explanations

geographical locations and proper nouns related to places

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 handle

-0.50

 BoxFit

-0.49

 nature

-0.48

 count

-0.47

 trade

-0.47

AndEndTag

-0.46

 laikā

-0.45

lī

-0.43

sub

-0.42

sla

-0.42

POSITIVE LOGITS

principalTable

0.80

tvguidetime

0.75

 Савезне

0.72

DeleteBehavior

0.71

 stoneware

0.71

 Hague

0.71

 demurrer

0.69

verwijspagina

0.69

onViewCreated

0.66

 trier

0.66

Activations Density 0.271%

geographical locations and proper nouns related to places

No Comments

No Known Activations

geographical locations and proper nouns related to places

No Comments

No Known Activations