INDEX

Explanations

mentions of the location "Ontario" in different contexts

oai_token-act-pair · gpt-3.5-turbo

references to the province of Ontario

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

bler

-0.93

eting

-0.78

ãĤ©

-0.77

ader

-0.76

geist

-0.75

gers

-0.75

Afee

-0.71

 Ferdinand

-0.70

ãĥ¼ãĥĨ

-0.70

ging

-0.70

POSITIVE LOGITS

 Provincial

1.29

 Ontario

0.97

NDP

0.95

 provincial

0.94

Canada

0.91

 Superior

0.90

 Canada

0.90

 province

0.88

incial

0.86

 Centre

0.85

Activations Density 0.027%

mentions of the location "Ontario" in different contexts

references to the province of Ontario

No Comments

No Known Activations