INDEX

Explanations

strings related to computer programming and data handling, particularly focusing on coded instructions

oai_token-act-pair · gpt-3.5-turbo

statements of existence or definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

osate

-0.76

 Lack

-0.73

endon

-0.68

 Improve

-0.65

rench

-0.63

 Isles

-0.62

 Dare

-0.61

ionics

-0.61

 Breach

-0.59

 Critics

-0.59

POSITIVE LOGITS

 usually

1.30

 typically

1.14

 supposed

1.10

 then

1.02

 indistinguishable

1.01

 comprised

1.00

 essentially

1.00

 assumed

1.00

 basically

0.99

 treated

0.97

Activations Density 0.288%

strings related to computer programming and data handling, particularly focusing on coded instructions

statements of existence or definitions

No Comments

No Known Activations