INDEX

Explanations

phrases indicating source or origin

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ActiveRecord

-0.56

сник

-0.51

duled

-0.50

aksanaan

-0.50

لبية

-0.49

fie

-0.48

řské

-0.46

 hayal

-0.46

écriture

-0.46

DULE

-0.45

POSITIVE LOGITS

 whence

1.05

 kaynağından

1.02

 therefrom

1.01

から

0.94

 Whence

0.93

FROM

0.93

 ifrån

0.92

whence

0.90

부터

0.88

 thence

0.88

Activations Density 0.097%

phrases indicating source or origin

No Comments

No Known Activations