INDEX

Explanations

links instructing users to click for further information or action

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to" and its variations, indicating directives or calls to action

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

existent

-0.73

quickShipAvailable

-0.70

 Kinnikuman

-0.63

existence

-0.63

ELD

-0.61

offensive

-0.58

][

-0.56

tein

-0.56

furt

-0.55

 Mechdragon

-0.55

POSITIVE LOGITS

 learn

1.39

 download

1.22

 browse

1.20

 subscribe

1.17

see

1.16

 find

1.14

 receive

1.13

 submit

1.12

 navigate

1.11

 discover

1.10

Activations Density 0.083%

links instructing users to click for further information or action

instances of the word "to" and its variations, indicating directives or calls to action

No Comments

No Known Activations