INDEX

Explanations

nouns and proper nouns in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

脚注の使い方

-1.33

تقاوى

-1.01

AccessorTable

-0.99

躇

-0.86

WithIOException

-0.86

 ProtoMessage

-0.81

WriteTagHelper

-0.81

ContentAsync

-0.80

AddTagHelper

-0.77

 propOrder

-0.77

POSITIVE LOGITS

 attractions

0.71

 tourist

0.68

 sightseeing

0.63

 sights

0.62

 attraction

0.60

 Visit

0.58

 visit

0.57

attra

0.57

 visited

0.56

 bezoek

0.55

Activations Density 0.120%

nouns and proper nouns in the text

No Comments

No Known Activations