INDEX

Explanations

words related to furniture

oai_token-act-pair · gpt-3.5-turbo

references to various types of furniture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

awar

-0.72

aneously

-0.68

-0.67

ceed

-0.67

-0.65

CNS

-0.65

olics

-0.64

ilitary

-0.62

Mub

-0.62

ounty

-0.60

POSITIVE LOGITS

 furniture

1.16

 decoration

0.98

iture

0.93

 drawer

0.90

 decorations

0.86

 arrang

0.83

 chairs

0.82

 shelves

0.81

pillar

0.76

etry

0.75

Activations Density 0.027%

words related to furniture

references to various types of furniture

No Comments

No Known Activations