INDEX

Explanations

comparative statements where someone or something is considered superior to another

oai_token-act-pair · gpt-3.5-turbo

comparative phrases establishing superiority or inferiority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 incorporation

-0.67

UCT

-0.66

 redress

-0.65

 explor

-0.65

 stabilization

-0.65

 rupture

-0.64

 resemb

-0.64

 cancellation

-0.64

 antic

-0.64

 blot

-0.63

POSITIVE LOGITS

 others

0.95

average

0.94

 anybody

0.94

 peers

0.85

 teammates

0.82

 everybody

0.82

 anyone

0.81

 yourselves

0.80

 everyone

0.79

agons

0.78

Activations Density 0.212%

comparative statements where someone or something is considered superior to another

comparative phrases establishing superiority or inferiority

No Comments

No Known Activations