INDEX

Explanations

phrases related to a specific person, job, or entity being in a particular place or position

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

irection

-0.66

inventoryQuantity

-0.66

iston

-0.64

Magikarp

-0.64

Methods

-0.63

Introduction

-0.63

upon

-0.63

Types

-0.63

amiya

-0.62

uish

-0.61

POSITIVE LOGITS

 verge

1.14

 sidelines

1.09

 brink

1.06

 planet

1.04

 payroll

1.01

 scene

0.97

 chopping

0.96

 lookout

0.96

 board

0.94

 list

0.93

Activations Density 0.120%

phrases related to a specific person, job, or entity being in a particular place or position

occurrences of the word "the."

No Comments

No Known Activations