INDEX

Explanations

tags or labels within a text

oai_token-act-pair · gpt-3.5-turbo

specific tags and names related to posts or articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bish

-0.86

MpServer

-0.71

Bir

-0.70

ÃŃs

-0.69

 compe

-0.69

atta

-0.68

aha

-0.68

ctica

-0.66

phrine

-0.65

illi

-0.64

POSITIVE LOGITS

Tags

2.35

 Courier

1.87

 Valentine

1.82

 Lowell

1.46

 Monroe

1.32

 Draper

1.29

 Kendall

1.23

 Marqu

1.23

 Tags

1.19

 Pepper

1.19

Activations Density 0.038%

tags or labels within a text

specific tags and names related to posts or articles

No Comments

No Known Activations