INDEX

Explanations

phrases related to physical spaces, particularly rooms

oai_token-act-pair · gpt-3.5-turbo

references to specific rooms in various contexts

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

Iss

-0.70

Uz

-0.64

merce

-0.62

elson

-0.62

HER

-0.61

 reconnect

-0.59

 landfall

-0.58

ushima

-0.58

BAT

-0.58

 Bonds

-0.58

POSITIVE LOGITS

room

1.10

 occupancy

1.01

rooms

0.97

 upstairs

0.92

 divid

0.92

 doors

0.92

 rooms

0.88

itory

0.87

clock

0.87

lain

0.83

Activations Density 0.047%

phrases related to physical spaces, particularly rooms

references to specific rooms in various contexts

No Comments

No Known Activations