INDEX

Explanations

action words related to user interface interactions, such as "add", "select", "click"

oai_token-act-pair · gpt-3.5-turbo

instructions and commands related to software functionalities

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

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

dfx

-0.78

yre

-0.70

 retard

-0.69

laz

-0.69

bably

-0.68

 assassins

-0.68

ĸļ

-0.67

cone

-0.67

 squats

-0.66

 physicists

-0.66

POSITIVE LOGITS

 Settings

1.27

 Selected

1.21

 Options

1.12

 Changes

1.09

 Preferences

1.06

 Parameters

1.06

 Info

1.05

 Mode

1.05

 Properties

1.04

 Contents

1.03

Activations Density 0.117%

action words related to user interface interactions, such as "add", "select", "click"

instructions and commands related to software functionalities

No Comments

No Known Activations