INDEX

Explanations

words related to reminders or memory triggers

oai_token-act-pair · gpt-3.5-turbo

instances of the word "remind" and its variations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

estern

-0.90

ccording

-0.78

 ILCS

-0.72

edom

-0.71

á

-0.70

EMS

-0.66

EH

-0.66

æĸ¹

-0.64

Bay

-0.64

HER

-0.64

POSITIVE LOGITS

ĸļ

1.03

 remind

1.00

 reminding

0.96

ingly

0.95

 reminders

0.89

 reminded

0.89

 reminder

0.87

 reminds

0.80

 vigilance

0.78

fulness

0.78

Activations Density 0.007%

words related to reminders or memory triggers

instances of the word "remind" and its variations

No Known Activations