INDEX

Explanations

phrases related to setting and achieving goals

oai_token-act-pair · gpt-3.5-turbo

references to goals and objectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 surgeon

-0.69

 counselor

-0.68

 maker

-0.67

 vendor

-0.66

 compar

-0.66

 passage

-0.66

 stud

-0.66

 suit

-0.65

 corpor

-0.65

rous

-0.64

POSITIVE LOGITS

 Goals

2.95

 Goal

2.60

Goal

1.70

GO

1.24

 Settings

1.13

 Away

1.12

 Shots

1.04

FG

1.04

 Plays

1.00

 Description

0.99

Activations Density 0.024%

phrases related to setting and achieving goals

references to goals and objectives

No Comments

No Known Activations