INDEX

Explanations

phrases related to guides or instructions

oai_token-act-pair · gpt-3.5-turbo

references to various guides or instructional content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 spect

-0.79

ulz

-0.74

erry

-0.71

oln

-0.70

 brighter

-0.65

 muted

-0.65

 derivative

-0.64

andel

-0.64

ensional

-0.63

asted

-0.63

POSITIVE LOGITS

 Guide

1.29

 Guides

1.13

Guide

1.08

guide

1.04

book

0.98

 Advice

0.94

 guide

0.94

books

0.90

 Tips

0.90

Tip

0.88

Activations Density 0.010%

phrases related to guides or instructions

references to various guides or instructional content

No Comments

No Known Activations