INDEX

Explanations

events, locations, and entities mentioned in news articles

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

otine

-0.68

 Mellon

-0.65

uliffe

-0.63

 Holding

-0.60

espie

-0.60

 Oaks

-0.59

cott

-0.58

ancy

-0.58

ļéĨĴ

-0.57

 Colon

-0.56

POSITIVE LOGITS

1.04

1.01

1.00

0.99

0.97

0.96

0.93

February

0.89

Activations Density 0.034%

events, locations, and entities mentioned in news articles

No Comments

No Known Activations