INDEX

Explanations

programming-related terms such as object names, functions, and data types

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

terday

-0.90

theless

-0.87

 captcha

-0.79

 territories

-0.71

 paran

-0.70

 highs

-0.70

 warming

-0.69

teness

-0.68

 hiatus

-0.66

 lows

-0.65

POSITIVE LOGITS

Manager

1.36

Field

1.34

Builder

1.34

Module

1.32

Component

1.32

Definition

1.30

Controller

1.30

Iterator

1.28

Property

1.27

Collection

1.23

Activations Density 0.075%

programming-related terms such as object names, functions, and data types

No Comments

No Known Activations