INDEX

Explanations

phrases related to transitions and new methods or technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

IntoConstraints

-1.03

 itſelf

-0.76

 Theſe

-0.76

CloseOperation

-0.71

 ſeveral

-0.70

 myſelf

-0.70

MigrationBuilder

-0.69

 HomeComponent

-0.68

 Monfieur

-0.68

 betrokken

-0.67

POSITIVE LOGITS

0.71

 standard

0.69

 system

0.59

0.58

 strict

0.57

 rather

0.57

0.56

 full

0.56

を採用

0.55

原則

0.53

Activations Density 0.493%

phrases related to transitions and new methods or technologies

No Comments

No Known Activations