INDEX

Explanations

instances of the word "explained" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 typelib

-0.76

دانشنامهٔ

-0.71

oredCriteria

-0.69

CardContent

-0.69

WEBPACK

-0.67

 AssemblyVersion

-0.66

NamedQuery

-0.66

CardBody

-0.65

enderror

-0.64

ChildScrollView

-0.63

POSITIVE LOGITS

 explained

1.13

explained

1.03

 Explained

0.92

 expliqué

0.81

 explicou

0.71

 explicado

0.69

 препратки

0.68

 explicó

0.66

 penjelasan

0.66

 Maximal

0.61

Activations Density 0.114%

instances of the word "explained" and related terms

No Comments

No Known Activations