INDEX

Explanations

phrases indicating suitability or recommendations for specific purposes or contexts

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

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

脚注の使い方

-1.00

 CreateTagHelper

-0.71

 HasFactory

-0.67

LookAnd

-0.66

 AssemblyCulture

-0.64

تقاوى

-0.62

 disponibilité

-0.62

 ویکی‌پدی

-0.61

__(/*!

-0.60

UnknownFieldSet

-0.59

POSITIVE LOGITS

 beginners

0.75

 occasions

0.69

 beginner

0.66

 busy

0.60

 young

0.60

 anyone

0.59

 vegans

0.59

Tracce

0.58

 kids

0.58

 vegetarians

0.57

Activations Density 0.180%

phrases indicating suitability or recommendations for specific purposes or contexts

No Comments

No Known Activations