INDEX

Explanations

references to places and events, particularly those related to Toronto

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations or places

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

 Liberia

-1.14

 Nevada

-1.07

 Paragu

-1.04

 Bundy

-1.03

 Boko

-0.99

 Petersen

-0.96

 Guinea

-0.96

 Wyoming

-0.95

Ãĥ

-0.93

 Idaho

-0.93

POSITIVE LOGITS

Toronto

2.12

TTC

2.01

 Toronto

1.92

 Scarborough

1.51

 Ontario

1.50

 Raptors

1.45

Ont

1.44

 Coun

1.36

 councillors

1.30

 Mississ

1.30

Activations Density 0.302%

references to places and events, particularly those related to Toronto

references to geographical locations or places

No Comments

No Known Activations