INDEX

Explanations

keywords or phrases between vertical bars

oai_token-act-pair · gpt-3.5-turbo

end-of-document markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tradem

-0.65

 reper

-0.64

 eleph

-0.61

ilty

-0.60

 exting

-0.60

 embargo

-0.57

anamo

-0.57

 estranged

-0.57

 amnesty

-0.57

 theirs

-0.57

POSITIVE LOGITS

Untitled

1.06

WASHINGTON

1.05

CLOSE

1.05

Abstract

1.05

Description

1.04

CTV

0.99

Overview

0.97

Still

0.96

Trivia

0.94

Breaking

0.93

Activations Density 0.109%

keywords or phrases between vertical bars

end-of-document markers

No Comments

No Known Activations