INDEX

Explanations

references to standards in various contexts

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

="@+

-0.67

 indisponible

-0.67

Morfologia

-0.62

Personensuche

-0.61

 mergeFrom

-0.60

 typical

-0.58

upol

-0.57

 beginnetje

-0.57

 урна

-0.56

CloseOperation

-0.56

POSITIVE LOGITS

 Standard

1.39

Standard

1.17

 Normal

0.83

Normal

0.82

 STANDARD

0.80

Simple

0.79

 Generale

0.75

 Simple

0.74

 General

0.74

 Standards

0.74

Activations Density 0.119%

references to standards in various contexts

No Comments

No Known Activations