INDEX

Explanations

lists or collections of items

oai_token-act-pair · gpt-3.5-turbo

instances of textual separation or markers indicating the structure of a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aeus

-0.71

administ

-0.69

ei

-0.68

managed

-0.64

istration

-0.62

ifice

-0.62

oni

-0.61

gery

-0.61

istence

-0.61

stretched

-0.61

POSITIVE LOGITS

 Reasons

1.39

 Ways

1.11

 reasons

1.10

 Worst

1.06

 Things

1.00

 ways

0.99

 Tips

0.95

 myths

0.95

 Greatest

0.93

 Signs

0.93

Activations Density 0.136%

lists or collections of items

instances of textual separation or markers indicating the structure of a document

No Comments

No Known Activations