INDEX

Explanations

parameters and context in function definitions and API requests

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

Code snippets or code-related terms

np_acts-logits-general · gemini-2.0-flash

computational context or programming code

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

ne

-0.49

 suit

-0.48

ه

-0.44

 both

-0.43

athe

-0.42

使

-0.41

 vậy

-0.41

доне

-0.41

he

-0.40

ָא

-0.40

POSITIVE LOGITS

 الرياضيه

1.05

 الحره

1.03

vician

0.99

 Wikimedijinoj

0.95

InjectAttribute

0.92

WebElementEntity

0.91

tagext

0.90

UnsafeEnabled

0.89

tanleria

0.88

featureID

0.87

Activations Density 0.097%

parameters and context in function definitions and API requests

Code snippets or code-related terms

computational context or programming code

No Comments

No Known Activations