INDEX

Explanations

code related to making HTTP requests

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

HTTP request methods (PUT, GET, POST, etc.)

np_acts-logits-general · gemini-2.0-flash

HTTP methods

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

IUrlHelper

-0.51

InjectAttribute

-0.50

 '\\;'

-0.49

 Waterfront

-0.48

 freckles

-0.47

 heavenly

-0.46

👓

-0.46

WaitGroup

-0.46

 Scand

-0.45

timeScale

-0.45

POSITIVE LOGITS

 post

1.34

 POST

1.28

POST

1.25

post

1.21

 Post

1.17

Post

1.11

 пост

0.92

GET

0.91

GET

0.90

PUT

0.78

Activations Density 0.103%

code related to making HTTP requests

HTTP request methods (PUT, GET, POST, etc.)

HTTP methods

No Comments

No Known Activations