INDEX

Explanations

references to the city of Toronto

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Toronto"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

mble

-0.86

hardt

-0.80

bler

-0.76

vana

-0.75

hard

-0.74

ktop

-0.71

warts

-0.70

vier

-0.70

inelli

-0.70

ãĤ©

-0.70

POSITIVE LOGITS

 Raptors

0.97

 Argon

0.91

 Harbour

0.91

 Heights

0.86

 Toronto

0.85

 Maple

0.82

 Centre

0.82

 skyline

0.79

 Citiz

0.75

FC

0.74

Activations Density 0.010%

references to the city of Toronto

occurrences of the word "Toronto"

No Comments

No Known Activations