INDEX

Explanations

proper nouns, particularly names and places, related to specific individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ed

-0.68

ngdoc

-0.58

 trời

-0.58

ERAS

-0.54

omock

-0.53

didSet

-0.50

ecap

-0.50

ますが

-0.49

ي

-0.49

whole

-0.49

POSITIVE LOGITS

ChildIndex

0.61

lean

0.56

 فريبيس

0.56

#+#

0.55

licon

0.54

 indipendente

0.54

 UIAlert

0.51

 صوتيه

0.50

voorbeeld

0.50

saraba

0.49

Activations Density 0.161%

proper nouns, particularly names and places, related to specific individuals and organizations

No Comments

No Known Activations