INDEX

Explanations

terms related to requests in a programming or API context

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

"request" and related terms

np_acts-logits-general · gemini-2.0-flash

request and variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

principalColumn

-0.78

findpost

-0.78

viewDidLoad

-0.74

ViewInit

-0.73

merie

-0.70

AfterClass

-0.70

LookAnd

-0.69

InputBorder

-0.69

 ujednoznacz

-0.68

aarrggbb

-0.68

POSITIVE LOGITS

 getRequest

0.81

 requests

0.75

 Request

0.72

AnimationFrame

0.70

 Requests

0.69

getRequest

0.68

Requests

0.66

 request

0.65

requests

0.64

 REQUEST

0.62

Activations Density 0.085%

terms related to requests in a programming or API context

"request" and related terms

request and variations

No Comments

No Known Activations