INDEX

Explanations

commands related to enabling and disabling features

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

apest

-1.15

llah

-0.84

axies

-0.78

ioxide

-0.72

ivan

-0.71

ortment

-0.71

ĸļ

-0.71

itar

-0.70

iday

-0.68

 Fernand

-0.68

POSITIVE LOGITS

Disable

0.89

 automatic

0.84

 javascript

0.79

 Genie

0.76

 switches

0.73

 disable

0.73

 permissions

0.73

 DEBUG

0.71

 boolean

0.70

 installs

0.70

Activations Density 0.033%

commands related to enabling and disabling features

No Comments

No Known Activations