INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

!/

-0.66

actionDate

-0.65

abc

-0.63

protection

-0.63

 ANGEL

-0.62

 maid

-0.62

 Mandatory

-0.62

wcs

-0.61

å§

-0.61

terior

-0.60

POSITIVE LOGITS

 himself

0.94

Sr

0.89

 recalls

0.84

Jr

0.80

 admits

0.79

 enjoys

0.77

 recounts

0.76

 wandered

0.75

 spends

0.73

 underwent

0.73

Activations Density 0.255%

proper nouns

No Comments

No Known Activations