INDEX

Explanations

directives prompting action or reminding about something

oai_token-act-pair · gpt-3.5-turbo

repeated phrases encouraging action or reminders

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

cheat

-0.80

Released

-0.80

ItemTracker

-0.78

é¾

-0.74

abase

-0.67

 PsyNet

-0.66

aughtered

-0.66

inals

-0.64

isine

-0.63

Arab

-0.63

POSITIVE LOGITS

fulness

0.72

 remembered

0.69

theless

0.68

ful

0.68

fully

0.67

 sweets

0.65

 classics

0.64

pieces

0.64

 remembering

0.64

fort

0.62

Activations Density 0.012%

directives prompting action or reminding about something

repeated phrases encouraging action or reminders

No Comments

No Known Activations