INDEX

Explanations

phrases related to ethical or legal obligations

oai_token-act-pair · gpt-3.5-turbo

references to obligations and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

vae

-0.79

ergy

-0.78

 Blueprint

-0.74

 Missile

-0.72

 Iter

-0.67

 Lans

-0.67

 Tate

-0.66

 Ellison

-0.65

ogene

-0.65

estamp

-0.65

POSITIVE LOGITS

 duty

1.27

duty

1.11

 Duty

1.02

uty

0.96

 duties

0.91

 obligation

0.90

 obligations

0.87

 honoured

0.80

 allegiance

0.78

 refres

0.78

Activations Density 0.011%

phrases related to ethical or legal obligations

references to obligations and responsibilities

No Comments

No Known Activations