INDEX

Explanations

numeric measurements in the form of negative values

oai_token-act-pair · gpt-3.5-turbo

phrases related to financial or economic concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Kern

-0.83

 Arabian

-0.73

 Jelly

-0.73

 Desert

-0.72

 Cotton

-0.71

 Cree

-0.69

 Crab

-0.69

Sea

-0.69

 steam

-0.67

Cum

-0.67

POSITIVE LOGITS

related

1.41

based

1.33

driven

1.27

oriented

1.24

intensive

1.24

sensitive

1.23

seeking

1.20

laden

1.18

producing

1.16

saving

1.16

Activations Density 0.113%

numeric measurements in the form of negative values

phrases related to financial or economic concepts

No Comments

No Known Activations