INDEX

Explanations

mentions of specific keywords in text, such as names, places, or dates

oai_token-act-pair · gpt-3.5-turbo

newline or paragraph break markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tradem

-0.78

 reper

-0.75

 amnesty

-0.71

 eleph

-0.71

ilty

-0.70

 exting

-0.69

 estranged

-0.69

 embargo

-0.69

 theirs

-0.68

 sovereignty

-0.67

POSITIVE LOGITS

Untitled

1.19

CLOSE

1.18

WASHINGTON

1.17

Description

1.17

Abstract

1.15

CTV

1.11

Still

1.09

Overview

1.09

Trivia

1.09

Breaking

1.06

Activations Density 0.105%

mentions of specific keywords in text, such as names, places, or dates

newline or paragraph break markers

No Comments

No Known Activations