INDEX

Explanations

phrases related to statements or positions on particular topics

oai_token-act-pair · gpt-3.5-turbo

verbs indicating advocacy, defense, or emotional response in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Ther

-0.76

wayne

-0.68

 ILCS

-0.66

window

-0.64

opus

-0.64

brance

-0.63

scribe

-0.62

Base

-0.61

Contents

-0.61

ãĥİ

-0.61

POSITIVE LOGITS

 sarcast

0.82

anke

0.74

 Wednesday

0.74

 Thursday

0.74

 Tuesday

0.73

 dismiss

0.68

 Monday

0.67

 upbeat

0.66

 yesterday

0.66

 brisk

0.66

Activations Density 0.222%

phrases related to statements or positions on particular topics

verbs indicating advocacy, defense, or emotional response in discussions

No Comments

No Known Activations