INDEX

Explanations

texts related to principles and guidelines

oai_token-act-pair · gpt-3.5-turbo

concepts related to guiding principles or values

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

icter

-0.77

ovies

-0.76

umbn

-0.74

 outage

-0.73

OVA

-0.72

 Cros

-0.69

ourcing

-0.68

scene

-0.68

gallery

-0.66

usercontent

-0.65

POSITIVE LOGITS

 principles

1.35

 tenets

1.28

 guiding

1.24

 Principles

1.24

 precept

1.10

 commandments

1.07

 formulated

1.05

 foundational

1.03

 principle

1.01

 dictates

1.00

Activations Density 0.567%

texts related to principles and guidelines

concepts related to guiding principles or values

No Comments

No Known Activations