INDEX

Explanations

instances of code snippets or programming-related content

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 eleph

-0.70

.""

-0.70

hement

-0.67

 spokes

-0.66

 prosec

-0.65

 Burgess

-0.64

 Burnett

-0.62

 Hancock

-0.61

abouts

-0.61

 traveling

-0.60

POSITIVE LOGITS

Installation

1.09

Async

1.07

Requirements

1.05

Usage

1.05

Testing

1.04

Python

1.00

ÂłÂłÂł

0.99

Contribut

0.98

Overview

0.97

aspx

0.94

Activations Density 0.238%

instances of code snippets or programming-related content

No Comments

No Known Activations