INDEX

Explanations

entities that categorize various methods and classifications within a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Personensuche

-0.51

制

-0.49

ждается

-0.49

GraphicsUnit

-0.48

IndentedString

-0.48

曖昧さ回避

-0.47

PasswordField

-0.47

hede

-0.45

 disponibilités

-0.45

 кӀ

-0.44

POSITIVE LOGITS

 belongs

2.13

 belong

2.09

belong

1.80

 belonged

1.77

 belonging

1.74

belongs

1.56

 pertenece

1.50

 Belong

1.50

 apparti

1.45

 appartient

1.44

Activations Density 0.944%

entities that categorize various methods and classifications within a scientific context

No Comments

No Known Activations