INDEX

Explanations

various forms and contexts of the word "light."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 оригіналу

-0.90

 MainAxisSize

-0.89

Geplaatst

-0.74

 AssemblyTitle

-0.72

esModule

-0.71

 consultato

-0.70

RegistryLite

-0.69

ElementException

-0.68

webElement

-0.64

AddTagHelper

-0.63

POSITIVE LOGITS

bulb

0.92

hearted

0.87

nings

0.84

ened

0.77

 bulb

0.73

heartedly

0.71

ening

0.71

NING

0.70

 bulbs

0.67

 hearted

0.65

Activations Density 0.116%

various forms and contexts of the word "light."

No Comments

No Known Activations