INDEX

Explanations

web addresses

oai_token-act-pair · gpt-3.5-turbo

website references and email addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Scheme

-0.90

 Fundamental

-0.83

 Ninth

-0.72

 Principle

-0.69

 Conclusion

-0.69

ANG

-0.68

CONCLUS

-0.68

 recourse

-0.68

ï¸

-0.67

 Advocate

-0.66

POSITIVE LOGITS

0.99

fp

0.93

yp

0.93

0.92

aber

0.90

rl

0.86

ibrary

0.86

leep

0.85

mc

0.85

fd

0.84

Activations Density 0.266%

web addresses

website references and email addresses

No Comments

No Known Activations