INDEX

Explanations

specific names and terms, particularly related to 'draw' or 'drag', in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

homonymie

-0.62

 '\\;'

-0.61

+#+

-0.58

 архивлан

-0.56

TestingModule

-0.56

rungsseite

-0.56

onAttach

-0.55

 تضيفلها

-0.52

 estimés

-0.51

oulli

-0.50

POSITIVE LOGITS

 NSCoder

0.70

CodedInputStream

0.63

ModelSerializer

0.61

 useStyles

0.57

HandlerContext

0.52

parametrize

0.49

invokeLater

0.49

Drop

0.49

 échange

0.48

UpInside

0.48

Activations Density 0.710%

specific names and terms, particularly related to 'draw' or 'drag', in various contexts

No Comments

No Known Activations