INDEX

Explanations

references to the Humane Society organization

oai_token-act-pair · gpt-3.5-turbo

references to the Humane Society and discussions about animal welfare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

indal

-0.85

kj

-0.79

andals

-0.76

aden

-0.74

 Cruiser

-0.74

berries

-0.74

amina

-0.73

annis

-0.72

acular

-0.72

peak

-0.70

POSITIVE LOGITS

 Humane

1.01

 humane

0.98

humane

0.77

ly

0.77

 society

0.76

 manner

0.75

 Slaughter

0.74

Ĥª

0.74

 tract

0.73

 slaughter

0.72

Activations Density 0.021%

references to the Humane Society organization

references to the Humane Society and discussions about animal welfare

No Comments

No Known Activations