INDEX

Explanations

mentions of the province of Ontario

oai_token-act-pair · gpt-3.5-turbo

mentions of 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bler

-0.90

riz

-0.85

ãĥķ

-0.85

ãĤ·ãĥ£

-0.83

enance

-0.82

gers

-0.81

letcher

-0.81

ãĤ©

-0.81

iesta

-0.79

cies

-0.79

POSITIVE LOGITS

 Provincial

0.98

 Superior

0.82

 Heights

0.81

 Ontario

0.76

 Centre

0.72

 Canada

0.71

 conferred

0.70

 Universities

0.69

 Hydro

0.69

 Pradesh

0.68

Activations Density 0.017%

mentions of the province of Ontario

mentions of the province of Ontario

No Comments

No Known Activations