INDEX

Explanations

number or code-related patterns and entities

oai_token-act-pair · gpt-3.5-turbo

symbols or characters related to financial or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Stard

-0.79

oted

-0.70

Peb

-0.68

 Jelly

-0.67

 Berks

-0.65

Ivy

-0.63

 Wiley

-0.61

 ancest

-0.61

 Indian

-0.61

 Middles

-0.61

POSITIVE LOGITS

âĤ¬

1.19

Ëľ

1.09

Â¢

0.93

Ã¯

0.93

chal

0.92

Â£

0.90

 âĤ¬

0.86

Ì¶

0.85

hyde

0.83

Activations Density 0.004%

number or code-related patterns and entities

symbols or characters related to financial or programming contexts

No Comments

No Known Activations