INDEX

Explanations

numerical values and measurements indicating distance, temperature, or physical attributes

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

Hide

-0.69

tnc

-0.65

 scapego

-0.64

rador

-0.62

à¨

-0.62

 reneg

-0.62

ç·

-0.61

 jealousy

-0.58

 nurture

-0.56

ESE

-0.56

POSITIVE LOGITS

 total

1.24

total

1.13

illion

1.02

 apiece

1.02

 counting

0.99

 average

0.96

 averaged

0.96

 compared

0.95

 TOTAL

0.93

 averaging

0.91

Activations Density 6.657%

numerical values and measurements indicating distance, temperature, or physical attributes

No Comments

No Known Activations