INDEX

Explanations

phrases indicating personal growth and introspection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

IntoConstraints

-0.65

logrus

-0.58

ResponseWriter

-0.57

endregion

-0.54

SocketChannel

-0.54

badlogic

-0.53

出版年

-0.53

UserScript

-0.53

IActionResult

-0.52

bigliamento

-0.52

POSITIVE LOGITS

 appreciation

1.08

 appreciate

1.05

 appreciating

0.97

 understand

0.95

 understanding

0.94

 Appreciate

0.90

 appreciates

0.90

 appreciated

0.89

 understood

0.87

 realize

0.87

Activations Density 0.255%

phrases indicating personal growth and introspection

No Comments

No Known Activations