INDEX

Explanations

words related to urgency and pressing issues

oai_token-act-pair · gpt-3.5-turbo

expressions of urgency or immediate need

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

wagen

-0.83

elson

-0.82

edin

-0.79

gemony

-0.79

ramid

-0.76

owitz

-0.75

essee

-0.74

aunder

-0.73

arthed

-0.73

©¶æ

-0.71

POSITIVE LOGITS

 urgency

1.13

 urgent

1.04

 urgently

0.93

 necessity

0.91

 concern

0.90

 proble

0.89

 imperative

0.81

 priority

0.80

 notifications

0.78

 demand

0.78

Activations Density 0.024%

words related to urgency and pressing issues

expressions of urgency or immediate need

No Comments

No Known Activations