INDEX

Explanations

questions that begin with "how do" or similar variations

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

LookAnd

-0.53

IContainer

-0.51

xfe

-0.50

http

-0.49

Explicación

-0.48

aŭ

-0.47

selves

-0.47

судар

-0.47

//

-0.47

idados

-0.46

POSITIVE LOGITS

strptime

0.73

enumi

0.73

NameInMap

0.69

?''

0.69

twimg

0.68

ScopeManager

0.68

 gainera

0.67

 inégal

0.67

 indisponible

0.66

Peacock

0.66

Activations Density 0.161%

questions that begin with "how do" or similar variations

No Comments

No Known Activations