INDEX

Explanations

phrases related to furniture

oai_token-act-pair · gpt-3.5-turbo

references to pieces of furniture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aneously

-0.67

 Ibid

-0.64

irgin

-0.63

ounty

-0.63

 Violent

-0.63

————

-0.62

awar

-0.62

mary

-0.61

ml

-0.61

olics

-0.61

POSITIVE LOGITS

 furniture

1.33

iture

1.01

 decoration

0.99

 decorations

0.94

 chairs

0.94

 drawer

0.89

 Furn

0.81

 Crate

0.80

ronics

0.77

pillar

0.76

Activations Density 0.019%

phrases related to furniture

references to pieces of furniture

No Comments

No Known Activations