INDEX

Explanations

proper nouns related to locations and names

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ishers

-0.72

arty

-0.63

ered

-0.62

acts

-0.61

ship

-0.61

ries

-0.60

ously

-0.59

istically

-0.59

istic

-0.58

ghai

-0.57

POSITIVE LOGITS

peed

1.28

aurus

1.26

ync

1.25

sein

1.23

hip

1.22

ystem

1.21

mith

1.20

ource

1.20

CRIP

1.19

erver

1.18

Activations Density 1.471%

proper nouns related to locations and names

No Comments

No Known Activations