INDEX

Explanations

specific words and phrases related to identification or categorization within a context

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

that can be initialisms

np_acts-logits-general · gemini-2.0-flash

proper noun phrases

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 tartalomajánló

-0.98

 الرياضيه

-0.86

AntiForgeryToken

-0.86

CloseOperation

-0.85

VersionUID

-0.83

EDEFAULT

-0.81

 ainfi

-0.79

 disponibilités

-0.79

 GoogleFonts

-0.78

 surla

-0.77

POSITIVE LOGITS

PhysRev

0.61

Ed

0.57

Ed

0.55

Sa

0.54

gar

0.54

Pyx

0.53

Ly

0.53

van

0.53

Gar

0.52

ik

0.52

Activations Density 0.802%

specific words and phrases related to identification or categorization within a context

that can be initialisms

proper noun phrases

No Comments

No Known Activations