INDEX

Explanations

keywords related to numerical values, specifically focusing on density measurements

oai_token-act-pair · gpt-3.5-turbo

references to physical density 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

eem

-0.74

 Reneg

-0.73

encer

-0.69

 Money

-0.68

wu

-0.66

HM

-0.66

 laps

-0.66

 apologised

-0.64

login

-0.63

 Merc

-0.62

POSITIVE LOGITS

 density

3.78

 dens

2.91

density

2.79

 dense

1.72

ensity

1.65

 thickness

1.37

 ratio

1.30

 ratios

1.24

 richness

1.24

 intensity

1.20

Activations Density 0.017%

keywords related to numerical values, specifically focusing on density measurements

references to physical density in various contexts

No Comments

No Known Activations