INDEX

Explanations

text related to the end of a document or section

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation or other symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 eleph

-0.71

 reper

-0.63

 forks

-0.60

 circulation

-0.59

 tradem

-0.59

 theirs

-0.59

 sacrificed

-0.58

 withdrawal

-0.58

 interven

-0.58

 estranged

-0.58

POSITIVE LOGITS

WASHINGTON

1.17

CLOSE

1.15

Abstract

1.14

Description

1.12

Untitled

1.11

Overview

1.06

Still

1.04

CTV

1.03

Breaking

1.03

CLE

1.03

Activations Density 0.119%

text related to the end of a document or section

instances of punctuation or other symbols

No Comments

No Known Activations