INDEX

Explanations

mentions related to Canada or Canadian entities

oai_token-act-pair · gpt-3.5-turbo

references to Canada and Canadian entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

mble

-0.93

oldemort

-0.83

rex

-0.81

bler

-0.79

inse

-0.76

itzer

-0.75

pty

-0.74

ãĥł

-0.74

swick

-0.73

iets

-0.73

POSITIVE LOGITS

 Forces

1.16

 Canadians

1.05

 Centre

0.97

istani

0.94

 Canadian

0.92

 Rockies

0.90

 Journalists

0.88

 Scotia

0.86

 Tire

0.83

 Geographic

0.82

Activations Density 0.011%

mentions related to Canada or Canadian entities

references to Canada and Canadian entities or concepts

No Comments

No Known Activations