INDEX

Explanations

annotations or documentation markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 فريبيس

-0.51

vician

-0.45

iausi

-0.44

mag

-0.40

EDEFAULT

-0.40

Finish

-0.38

harvard

-0.38

Tito

-0.38

 basically

-0.38

Clear

-0.38

POSITIVE LOGITS

 للاسماء

1.06

Datuak

1.05

__(/*!

0.95

 بيها

0.93

}")]

0.91

CloseOperation

0.84

 Accesat

0.84

 initComponents

0.81

("")]

0.79

__":

0.78

Activations Density 0.021%

annotations or documentation markers

No Comments

No Known Activations