INDEX

Explanations

technical terms related to software and programming

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

apego

-0.64

enegger

-0.54

oaded

-0.54

oppable

-0.54

iosyncr

-0.52

acebook

-0.52

inx

-0.51

 promot

-0.50

orsi

-0.49

redit

-0.49

POSITIVE LOGITS

 context

0.87

 vicinity

0.86

 guise

0.86

 nutshell

0.80

 manner

0.76

 circles

0.76

 contexts

0.74

 mode

0.73

 midst

0.71

 area

0.67

Activations Density 0.713%

technical terms related to software and programming

No Comments

No Known Activations