INDEX

Explanations

phrases related to varying degrees or levels of something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating degrees of measurement or assessment

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

 Andromeda

-0.74

enegger

-0.74

 Twins

-0.73

ãĥĹ

-0.72

ILLE

-0.71

vous

-0.69

sbm

-0.69

vertisements

-0.65

 Pelicans

-0.65

uter

-0.64

POSITIVE LOGITS

 crossings

0.87

level

0.86

 levels

0.84

 level

0.81

 assurance

0.76

ropri

0.75

 amounts

0.71

lining

0.69

 elevation

0.69

 quantities

0.67

Activations Density 0.033%

phrases related to varying degrees or levels of something

phrases indicating degrees of measurement or assessment

No Comments

No Known Activations