INDEX

Explanations

technical terms related to technology and engineering

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_fs12288-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

12,288

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

aminer

-0.76

 tremend

-0.75

 mathemat

-0.65

hered

-0.64

 intrins

-0.60

dyl

-0.60

 estab

-0.59

 suscept

-0.59

 slightest

-0.59

 scant

-0.59

POSITIVE LOGITS

adium

1.19

owing

1.17

ength

1.17

enged

1.16

iance

1.14

enge

1.10

ergic

1.07

ocated

1.07

ocations

1.04

enges

1.03

Activations Density 0.036%

technical terms related to technology and engineering

No Comments

No Known Activations