INDEX

Explanations

phrases related to self-identity and introspection

oai_token-act-pair · gpt-3.5-turbo

references to self-identity and personal definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 ratification

-0.81

 confisc

-0.79

 impeachment

-0.71

 moratorium

-0.69

 confiscated

-0.68

 shotguns

-0.68

 restart

-0.67

 irrigation

-0.67

 ringing

-0.67

 inspections

-0.65

POSITIVE LOGITS

 selves

1.12

 individuality

1.01

 persona

1.00

selves

0.90

lik

0.87

 personality

0.86

apeshifter

0.84

 oneself

0.84

eness

0.84

Person

0.83

Activations Density 0.421%

phrases related to self-identity and introspection

references to self-identity and personal definitions

No Comments

No Known Activations