INDEX

Explanations

place or location names, specifically focusing on Toronto

oai_token-act-pair · gpt-3.5-turbo

references related to the city of Toronto

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

abase

-0.80

ufact

-0.75

displayText

-0.69

ategory

-0.69

ruary

-0.66

enegger

-0.64

ktop

-0.63

heit

-0.62

 clot

-0.61

pard

-0.61

POSITIVE LOGITS

Ń·

0.79

®

0.76

©¶æ

0.75

é¾

0.72

Ĩ

0.69

¶æ

0.65

¾

0.65

obl

0.64

 Apex

0.64

echo

0.64

Activations Density 0.119%

place or location names, specifically focusing on Toronto

references related to the city of Toronto

No Comments

No Known Activations