INDEX

Explanations

phrases indicating responsibility or affiliation with an organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 ſel

-0.87

Efq

-0.87

 purpoſe

-0.86

 ſtre

-0.85

 ſta

-0.85

 ſte

-0.83

 tää

-0.83

 houſe

-0.83

 vastaan

-0.80

ſelf

-0.78

POSITIVE LOGITS

LookAnd

0.76

MessageOf

0.73

bewerken

0.73

PropertyChanging

0.70

jface

0.69

MigrationBuilder

0.69

WithIOException

0.68

complexContent

0.66

adpleegd

0.66

 neighboring

0.63

Activations Density 1.213%

phrases indicating responsibility or affiliation with an organization

No Comments

No Known Activations