INDEX

Explanations

terms related to technology and materials science, specifically focusing on surface area, efficiency, strength, and resistance

oai_token-act-pair · gpt-3.5-turbo

technical terms related to performance and efficiency metrics

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

arians

-0.71

atre

-0.65

ovie

-0.63

 haunt

-0.62

ozy

-0.62

anamo

-0.61

rius

-0.61

IRC

-0.60

entious

-0.59

Shy

-0.59

POSITIVE LOGITS

 characteristics

1.14

 coefficient

1.12

 capability

1.09

 ratio

1.03

 efficiency

1.03

 ratios

0.98

 capabilities

0.98

 achievable

0.97

 qualities

0.96

 Stability

0.96

Activations Density 0.216%

terms related to technology and materials science, specifically focusing on surface area, efficiency, strength, and resistance

technical terms related to performance and efficiency metrics

No Comments

No Known Activations