INDEX

Explanations

technical terminology and their implications in specific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 purpoſe

-0.75

 ſtate

-0.68

 pleaſure

-0.63

 تانيه

-0.62

 juſ

-0.62

IntoConstraints

-0.62

 Majefty

-0.61

 ſche

-0.60

 juſt

-0.59

 uſed

-0.58

POSITIVE LOGITS

 nonetheless

0.55

igshid

0.53

 nevertheless

0.53

 trotzdem

0.51

 dennoch

0.48

0.47

 EconPapers

0.47

Lähteet

0.45

الحياه

0.45

]")]

0.44

Activations Density 0.395%

technical terminology and their implications in specific contexts

No Comments

No Known Activations