INDEX

Explanations

patterns related to URL parsing and manipulation in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

and

-0.42

str

-0.41

bir

-0.40

 riso

-0.40

...

-0.39

 Curran

-0.38

ine

-0.38

__":

-0.38

 दौरान

-0.37

 vero

-0.36

POSITIVE LOGITS

OpenHelper

0.82

RectangleBorder

0.79

ViewFeatures

0.74

ReusableCell

0.73

StreetMap

0.70

 MainAxisSize

0.69

posables

0.69

脚注の使い方

0.69

IsMutable

0.68

UserScript

0.68

Activations Density 0.132%

patterns related to URL parsing and manipulation in code

No Comments

No Known Activations