INDEX

Explanations

health-related information and statistics

oai_token-act-pair · gpt-3.5-turbo

references to healthcare-related statistics or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 listeners

-0.67

players

-0.65

bay

-0.65

 illustrating

-0.64

handedly

-0.63

zai

-0.63

liam

-0.62

wo

-0.60

 anyone

-0.60

manship

-0.60

POSITIVE LOGITS

 same

1.23

 slightest

1.09

 dreaded

1.04

ses

1.01

 cheapest

0.98

 benefits

0.96

 safest

0.94

 requisite

0.94

ocratic

0.93

 fastest

0.89

Activations Density 0.327%

health-related information and statistics

references to healthcare-related statistics or information

No Comments

No Known Activations