INDEX

Explanations

items or tools that can be interacted with or switched out in a system

oai_token-act-pair · gpt-3.5-turbo

keywords related to physical items and infrastructure

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

Negative Logits

Was

-0.67

Was

-0.66

Said

-0.62

 Satanic

-0.61

Recomm

-0.56

 Investigator

-0.53

Lear

-0.52

 Died

-0.51

 Pieces

-0.50

Primary

-0.50

POSITIVE LOGITS

 abound

1.38

are

1.35

 aren

1.29

 tend

1.21

 seem

1.21

 have

1.19

 comprise

1.17

 remain

1.15

 embody

1.13

 thrive

1.10

Activations Density 0.546%

items or tools that can be interacted with or switched out in a system

keywords related to physical items and infrastructure

No Known Activations