INDEX

Explanations

phrases expressing positive sentiment, feedback, or reactions

oai_token-act-pair · gpt-3.5-turbo

expressions of positive feedback or responses

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

 someday

-0.79

sylvania

-0.68

tymology

-0.67

 Tycoon

-0.67

owe

-0.66

 Definition

-0.65

eday

-0.65

adium

-0.64

pta

-0.64

 lest

-0.64

POSITIVE LOGITS

 disappointing

1.38

cellent

1.37

 impressive

1.32

 pleasant

1.31

 lackluster

1.29

 satisfactory

1.23

 enjoyable

1.22

 pleasantly

1.20

whelming

1.18

 flawless

1.16

Activations Density 0.345%

phrases expressing positive sentiment, feedback, or reactions

expressions of positive feedback or responses

No Comments

No Known Activations