INDEX

Explanations

references to various forms of light and illumination

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

following "light"

np_acts-logits-general · gemini-2.0-flash

light + noun/verb combinations

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

 MainAxisSize

-0.84

 оригіналу

-0.79

RegistryLite

-0.74

Geplaatst

-0.72

enumii

-0.71

 consultato

-0.71

quelize

-0.68

AndEndTag

-0.67

 AssemblyTitle

-0.67

esModule

-0.67

POSITIVE LOGITS

bulb

0.91

nings

0.83

hearted

0.82

 bulb

0.73

heartedly

0.70

NING

0.70

ened

0.69

 bulbs

0.67

enment

0.66

ening

0.66

Activations Density 0.098%

references to various forms of light and illumination

following "light"

light + noun/verb combinations

No Comments

No Known Activations