INDEX

Explanations

references to programming configurations and file management

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

controlling your project to server

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 AssemblyTitle

-0.89

NameInMap

-0.82

 resourceCulture

-0.75

 Exacts

-0.70

 <<<<<<<<<<<<<<

-0.66

expandindo

-0.65

encodeWith

-0.65

InjectAttribute

-0.64

tagHelperRunner

-0.64

featureID

-0.64

POSITIVE LOGITS

 parlando

0.48

 assuming

0.47

 estando

0.43

 Assume

0.42

 دوران

0.42

再び

0.41

 tempore

0.40

 وقت

0.40

 zaman

0.38

avení

0.38

Activations Density 0.289%

references to programming configurations and file management

controlling your project to server

No Comments

No Known Activations