INDEX

Explanations

terms related to voltage and electrical concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

eworld

-0.81

pard

-0.80

iversary

-0.79

ctuary

-0.75

Bei

-0.73

chery

-0.72

ËĪ

-0.72

jon

-0.72

ointed

-0.70

iak

-0.70

POSITIVE LOGITS

 voltage

1.05

 fluctuations

1.02

 volts

1.02

 volt

0.93

 converter

0.92

 inputs

0.90

 amps

0.89

volt

0.84

 output

0.83

 surge

0.83

Activations Density 0.009%

terms related to voltage and electrical concepts

No Comments

No Known Activations