INDEX

Explanations

references to containers

oai_token-act-pair · gpt-3.5-turbo

references to containers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

bole

-0.81

olulu

-0.72

tz

-0.72

choes

-0.71

ramid

-0.71

hov

-0.70

OTO

-0.68

itters

-0.68

ongyang

-0.67

ichita

-0.66

POSITIVE LOGITS

 container

1.36

 containers

1.30

ainers

1.27

 Container

1.27

Container

0.95

vier

0.86

container

0.86

 vessel

0.81

 reef

0.78

iculture

0.77

Activations Density 0.006%

references to containers

references to containers

No Comments

No Known Activations