INDEX

Explanations

terms related to optimization and efficiency

oai_token-act-pair · gpt-3.5-turbo

terms related to optimization processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

soever

-0.78

ere

-0.76

FACE

-0.76

hips

-0.74

lie

-0.73

mad

-0.72

lain

-0.72

emonic

-0.69

lust

-0.69

onna

-0.68

POSITIVE LOGITS

 optimization

1.30

 optimize

1.25

 optim

1.25

 optimizing

1.09

 Optim

1.07

 optimizations

1.03

 optimized

0.89

fusc

0.86

 partName

0.84

optim

0.80

Activations Density 0.017%

terms related to optimization and efficiency

terms related to optimization processes

No Comments

No Known Activations