INDEX

Explanations

organizations related to animal welfare and terms related to ethical treatment of animals

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "humane" and organizations related to animal welfare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

andals

-0.81

indal

-0.77

berries

-0.73

 Cruiser

-0.72

acular

-0.72

arios

-0.71

oulos

-0.71

agers

-0.69

umar

-0.69

agne

-0.68

POSITIVE LOGITS

 humane

1.05

 Humane

0.99

ly

0.94

humane

0.82

 tract

0.78

TPPStreamerBot

0.73

 euth

0.72

 societies

0.72

 society

0.70

ELY

0.70

Activations Density 0.015%

organizations related to animal welfare and terms related to ethical treatment of animals

references to the concept of "humane" and organizations related to animal welfare

No Comments

No Known Activations