INDEX

Explanations

references to Canada and discussions related to it

oai_token-act-pair · gpt-3.5-turbo

the word "Canada" and related context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

-0.79

terior

-0.72

inse

-0.72

sym

-0.71

chest

-0.67

gered

-0.66

tops

-0.66

lihood

-0.66

ultan

-0.64

vae

-0.63

POSITIVE LOGITS

 Goose

1.15

 Tire

1.02

 Centre

0.94

 Revenue

0.93

 Scotia

0.91

 Forces

0.86

 Mortgage

0.86

 Bacon

0.86

 Border

0.85

 Institutes

0.84

Activations Density 0.046%

references to Canada and discussions related to it

the word "Canada" and related context

No Comments

No Known Activations