INDEX

Explanations

descriptions related to the optimization of processes and resources

oai_token-act-pair · gpt-3.5-turbo

concepts related to efficiency and optimization in processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

arling

-0.66

pires

-0.64

nered

-0.63

ogie

-0.62

igger

-0.61

omy

-0.61

Viol

-0.60

ricular

-0.60

Occup

-0.59

 stereotypical

-0.59

POSITIVE LOGITS

 eliminates

1.29

 avoids

1.24

 ensures

1.08

 seamlessly

1.04

 saves

1.02

 seamless

1.01

 eliminating

1.01

 easily

1.01

Allows

1.01

 effortlessly

1.01

Activations Density 0.536%

descriptions related to the optimization of processes and resources

concepts related to efficiency and optimization in processes

No Comments

No Known Activations