INDEX

Explanations

words related to furniture, specifically tables

oai_token-act-pair · gpt-3.5-turbo

references to dining or various types of tables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

vernment

-1.12

 Territories

-0.71

 Euras

-0.70

 Directorate

-0.69

ust

-0.69

é»Ĵ

-0.66

berto

-0.66

ï¸ı

-0.65

 Incarn

-0.64

natureconservancy

-0.63

POSITIVE LOGITS

cloth

1.53

tops

1.06

table

1.00

 table

0.98

 tables

0.95

 chairs

0.85

top

0.82

chair

0.81

stairs

0.81

sheet

0.80

Activations Density 0.012%

words related to furniture, specifically tables

references to dining or various types of tables

No Comments

No Known Activations