INDEX

Explanations

references to the company "General Electric" specifically

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

ï¸

-0.83

gypt

-0.77

bley

-0.74

ologies

-0.70

lihood

-0.69

nown

-0.68

gger

-0.68

gp

-0.64

pher

-0.63

some

-0.63

POSITIVE LOGITS

izations

1.09

 Electric

0.94

ization

0.92

 Dynamics

0.90

isations

0.90

 Motors

0.88

isation

0.85

ized

0.83

 Purpose

0.82

idad

0.81

Activations Density 0.014%

references to the company "General Electric" specifically

No Comments

No Known Activations