INDEX

Explanations

the word "And" starting sentences

oai_token-act-pair · gpt-3.5-turbo

instances of the word "And."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

icter

-0.67

icc

-0.67

imum

-0.66

entials

-0.65

iosyncr

-0.65

spir

-0.65

PDF

-0.63

ival

-0.62

Introduction

-0.62

operator

-0.62

POSITIVE LOGITS

 then

1.28

 secondly

1.26

 furthermore

1.23

 THEN

1.17

 yeah

1.17

romeda

1.06

hey

1.04

yet

1.02

 moreover

1.02

then

1.01

Activations Density 0.192%

the word "And" starting sentences

instances of the word "And."

No Comments

No Known Activations